© 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. 27-TRANSCODER-HP
    7. 57572
    Prev
    Next
    INDEX
    Explanations

    News or internet articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PUT
    -0.28
     REPL
    -0.27
     fitting
    -0.27
    iT
    -0.27
    illage
    -0.27
    -placement
    -0.26
    ResponseType
    -0.26
    fit
    -0.26
    placement
    -0.24
    .getProperty
    -0.24
    POSITIVE LOGITS
    abbr
    0.27
     insol
    0.26
    loating
    0.25
    INAL
    0.24
     numbers
    0.24
     trg
    0.24
    ération
    0.24
    ä¸įåıĹ
    0.23
    åIJĦ项
    0.23
     norms
    0.23
    Activations Density 0.000%

    No Known Activations