© 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. 59674
    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
    Not in Any Lists

    No Comments

    Negative Logits
     yıll
    -0.08
    面积
    -0.08
     Burr
    -0.07
    urar
    -0.07
     בחיים
    -0.07
    อาจจะ
    -0.07
    ’un
    -0.07
    쉰
    -0.07
    ˬ
    -0.06
    毵
    -0.06
    POSITIVE LOGITS
    inged
    0.07
     pacientes
    0.07
    draulic
    0.07
    杪
    0.07
    Packet
    0.07
    patial
    0.07
     Elect
    0.07
    _allocator
    0.07
    ]]></
    0.07
    Goods
    0.07
    Activations Density 0.019%

    No Known Activations