© 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. 71705
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    вести
    -0.07
     armed
    -0.07
     invert
    -0.06
     coraz
    -0.06
     �
    -0.06
    _ARCH
    -0.06
    冷笑
    -0.06
     petite
    -0.06
    您的
    -0.06
     Fort
    -0.06
    POSITIVE LOGITS
    _xlabel
    0.08
    얄
    0.07
     Lesbian
    0.07
    移民
    0.07
    蟊
    0.07
    的事实
    0.07
    /book
    0.07
    괞
    0.06
    иков
    0.06
    ика
    0.06
    Activations Density 0.003%

    No Known Activations