© 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. 81558
    Prev
    Next
    INDEX
    Explanations

    para

    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
    Not in Any Lists

    No Comments

    Negative Logits
    测评
    -0.07
     Announcement
    -0.07
    <
    -0.07
    byss
    -0.07
     psychology
    -0.07
     blanket
    -0.07
    场景
    -0.06
     Yin
    -0.06
    atch
    -0.06
    roll
    -0.06
    POSITIVE LOGITS
     הג
    0.08
    .Parcelable
    0.08
    rowad
    0.07
     awk
    0.07
     trả
    0.07
     intermedi
    0.07
     dzi
    0.07
    쩨
    0.07
     para
    0.07
    //}↵↵
    0.07
    Activations Density 0.059%

    No Known Activations