© 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. 15-RESID-POST-AA
    11. 3167
    Prev
    Next
    INDEX
    Explanations

    dialogue

    np_max-act · gemini-2.0-flash

    speaker identifiers and structural delimiters in formatted dialogue transcripts (e.g., placeholder name tags and turn separators).

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Acc
    -0.07
     Michel
    -0.07
    ="[
    -0.07
    하여
    -0.07
     Diseases
    -0.07
     NIR
    -0.07
    듭
    -0.07
    \D
    -0.07
    fact
    -0.07
    ح
    -0.07
    POSITIVE LOGITS
    榜样
    0.08
    伤亡
    0.07
    _gallery
    0.07
     эта
    0.07
     jeste
    0.07
    押
    0.07
     lie
    0.06
    媳
    0.06
     prognosis
    0.06
    /gpl
    0.06
    Activations Density 0.111%

    No Known Activations