© 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. 18624
    Prev
    Next
    INDEX
    Explanations

    user data snippets

    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
    垤
    -0.07
    liter
    -0.07
    明日
    -0.07
    _element
    -0.06
    慌
    -0.06
    unker
    -0.06
     mice
    -0.06
    멧
    -0.06
    online
    -0.06
    学校
    -0.06
    POSITIVE LOGITS
     SIP
    0.07
    禘
    0.07
    Remaining
    0.07
    につ
    0.07
     Bott
    0.07
    乌鲁木
    0.06
    ระยะ
    0.06
     Carlo
    0.06
     PackageManager
    0.06
     juego
    0.06
    Activations Density 0.031%

    No Known Activations