© 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. 94437
    Prev
    Next
    INDEX
    Explanations

    Quantum systems and environment

    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
    ℯ
    -0.07
    _gps
    -0.07
     "%.
    -0.07
    葭
    -0.07
    罨
    -0.07
    antry
    -0.07
    _migration
    -0.07
     Ago
    -0.06
    UDGE
    -0.06
    ḁ
    -0.06
    POSITIVE LOGITS
     restricting
    0.07
    サラ
    0.07
     specializes
    0.07
    	ext
    0.07
     beginner
    0.07
     World
    0.06
    expand
    0.06
     referendum
    0.06
     mega
    0.06
    הלך
    0.06
    Activations Density 0.016%

    No Known Activations