© 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. 17604
    Prev
    Next
    INDEX
    Explanations

    Q&A on various topics

    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
     full
    -0.07
     person
    -0.07
    钬
    -0.07
    ocom
    -0.07
    ewis
    -0.06
    oker
    -0.06
    相关信息
    -0.06
    .ft
    -0.06
    平均每
    -0.06
    _inverse
    -0.06
    POSITIVE LOGITS
     treaty
    0.08
     maxSize
    0.08
    てしまいました
    0.08
     jitter
    0.07
    羌
    0.07
     мя
    0.07
     стра
    0.07
    蚊
    0.07
     uuid
    0.06
    หา
    0.06
    Activations Density 0.152%

    No Known Activations