© 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. 12276
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
     correcting
    -0.07
    园
    -0.06
    徇
    -0.06
    CONDITION
    -0.06
     tempfile
    -0.06
    ött
    -0.06
    恸
    -0.06
    /f
    -0.06
     בית
    -0.06
     horse
    -0.06
    POSITIVE LOGITS
     FIFO
    0.08
     billboard
    0.07
     stroll
    0.07
    ratio
    0.07
    .isEmpty
    0.07
    .unpack
    0.07
    >I
    0.07
    市场需求
    0.07
     hi
    0.07
     burst
    0.07
    Activations Density 0.003%

    No Known Activations