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

    Neuronpedia

    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. 68835
    Prev
    Next
    INDEX
    Explanations

    comparisons/equality

    np_max-act · gemini-2.0-flash
    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
    Instance
    -0.07
     Havana
    -0.07
    🔈
    -0.07
     Venice
    -0.07
     Await
    -0.07
     hath
    -0.07
    ◇
    -0.07
    最
    -0.07
     الاحتلال
    -0.07
    depth
    -0.07
    POSITIVE LOGITS
    账
    0.09
    ski
    0.08
    irk
    0.07
    клад
    0.07
    渡
    0.07
    更多的
    0.07
    姊妹
    0.07
    headed
    0.07
    benef
    0.07
    學
    0.07
    Activations Density 0.013%

    No Known Activations