© 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. 19-RESID-POST-AA
    11. 48020
    Prev
    Next
    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    是一個
    -0.07
    桌上
    -0.07
    .delivery
    -0.06
     TestData
    -0.06
     Nodo
    -0.06
    变成
    -0.06
    	next
    -0.06
     נשאר
    -0.06
    üb
    -0.06
     struct
    -0.06
    POSITIVE LOGITS
    了不少
    0.08
    زيد
    0.07
     ju
    0.06
    見積
    0.06
    łam
    0.06
    _In
    0.06
    .singleton
    0.06
     Chart
    0.06
    Ease
    0.06
    ちなみ
    0.06
    Activations Density 0.004%

    No Known Activations