© 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. 18571
    Prev
    Next
    INDEX
    Explanations

    weight

    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
    Ber
    -0.08
    oris
    -0.07
    郑州
    -0.07
    _RSP
    -0.07
     Neal
    -0.07
     influencers
    -0.07
    是什么呢
    -0.07
     Julie
    -0.07
    unei
    -0.06
     reside
    -0.06
    POSITIVE LOGITS
    rays
    0.07
     Interval
    0.07
     名
    0.07
    ction
    0.07
    �
    0.07
     Arrival
    0.07
     Depths
    0.07
    我当时
    0.06
    特色社会
    0.06
     السنة
    0.06
    Activations Density 0.004%

    No Known Activations