© 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. 15-RESID-POST-AA
    11. 31356
    Prev
    Next
    INDEX
    Explanations

    Artificial intelligence

    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
    Negative Logits
     Farmer
    -0.07
    嫪
    -0.07
    gift
    -0.07
     출력
    -0.07
    Buzz
    -0.07
     camera
    -0.07
    zman
    -0.07
    �
    -0.06
    Pane
    -0.06
     produktów
    -0.06
    POSITIVE LOGITS
    .";↵
    0.07
    '>
    0.07
    .date
    0.07
    _inc
    0.07
    Canceled
    0.07
    س
    0.07
    ']=
    0.07
    years
    0.07
    ];//
    0.07
     나는
    0.07
    Activations Density 0.054%

    No Known Activations