© 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. 37244
    Prev
    Next
    INDEX
    Explanations

    expressions and voice

    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
    كشف
    -0.08
    身亡
    -0.07
     décou
    -0.07
     titles
    -0.07
     Hawks
    -0.07
    ación
    -0.07
     Clint
    -0.07
     düşün
    -0.07
     intersects
    -0.07
     Squad
    -0.07
    POSITIVE LOGITS
    综合治理
    0.07
    重点工作
    0.07
    {},
    0.07
    柢
    0.07
    𝐚
    0.07
     Examination
    0.07
     operating
    0.06
    免疫力
    0.06
    ทรง
    0.06
    ﻆ
    0.06
    Activations Density 0.031%

    No Known Activations