© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 63811
    Prev
    Next
    INDEX
    Explanations

    possessive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Built
    -0.28
    ester
    -0.25
    ace
    -0.25
     Rever
    -0.25
     Installed
    -0.25
     Beard
    -0.25
    Played
    -0.24
    Built
    -0.24
     Played
    -0.24
     emb
    -0.24
    POSITIVE LOGITS
    mando
    0.29
    人éĹ´
    0.29
    åij¨åĽ´çļĦ
    0.26
     nouveau
    0.25
    åİ¿åŁŁ
    0.25
    SystemService
    0.25
    르
    0.25
    propri
    0.24
    Suggestions
    0.24
    isors
    0.24
    Activations Density 18.096%

    No Known Activations