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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 2008
    Prev
    Next
    INDEX
    Explanations

    reality

    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
    spm
    -0.07
     seedu
    -0.07
    &page
    -0.07
    嗓
    -0.07
    圉
    -0.07
     đu
    -0.07
     House
    -0.07
    亩
    -0.07
    �
    -0.06
     pounds
    -0.06
    POSITIVE LOGITS
     reality
    0.11
     rubble
    0.08
     Aristotle
    0.08
     redemption
    0.07
    '})↵↵
    0.07
     Calibration
    0.07
    仪式
    0.07
    ']).
    0.07
     projecting
    0.07
    要在
    0.07
    Activations Density 0.007%

    No Known Activations