© 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. 7-RESID-POST-AA
    11. 37259
    Prev
    Next
    INDEX
    Explanations

    file paths and directories

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ද
    -0.08
    entric
    -0.07
    产品
    -0.07
    ridge
    -0.07
    ്�
    -0.07
    essen
    -0.07
    ā
    -0.07
    朝
    -0.07
    ி�
    -0.07
    🍣
    -0.07
    POSITIVE LOGITS
     april
    0.07
    这里的
    0.07
    ᕛ
    0.07
    	atomic
    0.07
    Дата
    0.07
    .scatter
    0.07
    :def
    0.07
     حال
    0.07
    ⛤
    0.07
    מפורט
    0.07
    Activations Density 0.187%

    No Known Activations