© 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. 30-TRANSCODER-HP
    7. 95885
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Disk
    -0.34
    Packages
    -0.33
     package
    -0.33
     Packages
    -0.32
    .package
    -0.31
    åĮħ
    -0.31
     packages
    -0.31
     disclosures
    -0.30
     declaration
    -0.29
    -package
    -0.29
    POSITIVE LOGITS
    éģĵ
    0.30
    oui
    0.28
    arse
    0.27
    计åĪĴ
    0.26
    è¿Ļç§įæĸ¹å¼ı
    0.25
     extrapol
    0.24
    andes
    0.24
    onne
    0.24
     Vive
    0.24
    Filed
    0.24
    Activations Density 1.170%

    No Known Activations