© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 19-RESID-POST-AA
    11. 20111
    Prev
    Next
    INDEX
    Explanations

    <

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    不经
    -0.08
    _glob
    -0.07
    脚下
    -0.07
     density
    -0.07
     NAFTA
    -0.07
    SHIFT
    -0.07
     relocation
    -0.07
     당시
    -0.07
    Arduino
    -0.07
    _dp
    -0.06
    POSITIVE LOGITS
    玫
    0.08
    РА
    0.07
    Pri
    0.07
    Elizabeth
    0.07
     challenged
    0.07
    (stage
    0.07
    	document
    0.06
    >{$
    0.06
    ategorical
    0.06
    这两种
    0.06
    Activations Density 0.032%

    No Known Activations