© 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. 31-TRANSCODER-HP
    7. 18149
    Prev
    Next
    INDEX
    Explanations

    Computer-related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĥĸ
    -0.26
    -dismissible
    -0.25
     liter
    -0.24
    atile
    -0.24
    andscape
    -0.24
    istle
    -0.24
    é»»
    -0.24
    react
    -0.24
     Ratings
    -0.24
     гÑĢаждан
    -0.23
    POSITIVE LOGITS
     Operator
    0.26
     forc
    0.26
    EXTERNAL
    0.25
    ieten
    0.25
    berger
    0.25
    cá
    0.25
    Ðģ
    0.24
    Installer
    0.24
    ritis
    0.24
    pios
    0.24
    Activations Density 0.017%

    No Known Activations