© 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. 73978
    Prev
    Next
    INDEX
    Explanations

    code-related punctuation

    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
     Celsius
    -0.07
     macOS
    -0.07
    ân
    -0.07
    越来越
    -0.07
     unheard
    -0.06
    房貸
    -0.06
     ransom
    -0.06
    㨳
    -0.06
    干净
    -0.06
    千古
    -0.06
    POSITIVE LOGITS
     study
    0.08
    interrupt
    0.08
     Stores
    0.08
    Holiday
    0.07
    .Repository
    0.07
     serializers
    0.07
    External
    0.07
    Digest
    0.07
    uffled
    0.07
    oints
    0.07
    Activations Density 0.050%

    No Known Activations