© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 74840
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    concise declarative assertions (often copular “X is Y” constructions) appearing at the ends of sentences.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pelosi
    -0.08
    AppDelegate
    -0.07
    sitemap
    -0.07
    bedtls
    -0.07
    챵
    -0.07
    ﭺ
    -0.06
    ưở
    -0.06
    .ComponentResourceManager
    -0.06
     jclass
    -0.06
    雎
    -0.06
    POSITIVE LOGITS
     hợp
    0.07
    -worker
    0.07
     projecting
    0.07
     gyr
    0.07
    writes
    0.07
    ค
    0.07
    割
    0.06
    س
    0.06
    できない
    0.06
     POSS
    0.06
    Activations Density 0.554%

    No Known Activations