© 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
    2. Qwen3-4B
    3. 25-TRANSCODER-HP
    4. 108767
    Prev
    Next
    INDEX
    Explanations

    Named entities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nage
    -0.30
     Mattis
    -0.27
    丧
    -0.25
    utow
    -0.24
    /dialog
    -0.23
     pyl
    -0.23
    æĤŁ
    -0.23
    éķĸ
    -0.23
    -handle
    -0.23
     currentPlayer
    -0.23
    POSITIVE LOGITS
    fax
    0.25
    Interest
    0.25
    æĬµæĬĹåĬĽ
    0.24
    idy
    0.24
     Interest
    0.23
     manh
    0.23
    çŃĸ
    0.23
    ereum
    0.23
     fixed
    0.23
    clud
    0.23
    Activations Density 1.367%

    No Known Activations