© 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. 15-RESID-POST-AA
    11. 40551
    Prev
    Next
    INDEX
    Explanations

    Text input fields (code)

    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_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
    _e
    -0.07
     UR
    -0.07
     launches
    -0.07
     Jay
    -0.07
    acons
    -0.07
     KP
    -0.06
    <|im_start|>
    -0.06
     Audio
    -0.06
    /native
    -0.06
     Julius
    -0.06
    POSITIVE LOGITS
    .memory
    0.07
    ゔ
    0.07
    ممارسة
    0.07
     Dresses
    0.07
    ԛ
    0.07
    垎
    0.06
    (length
    0.06
    .Length
    0.06
     שעל
    0.06
     Flesh
    0.06
    Activations Density 0.068%

    No Known Activations