© 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. 14-TRANSCODER-HP
    7. 40986
    Prev
    Next
    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çªĪ
    -0.28
    ä¸Ģ侧
    -0.27
    BU
    -0.27
    oir
    -0.26
    ev
    -0.26
    optic
    -0.26
    å¤ı天
    -0.25
     XK
    -0.25
    é¢Ħå¤ĩ
    -0.25
    EV
    -0.25
    POSITIVE LOGITS
    startIndex
    0.25
    æľŁåĨħ
    0.25
     algo
    0.24
    aram
    0.24
    lection
    0.24
    pects
    0.23
    ent
    0.23
    cci
    0.23
    .begin
    0.23
    .TryParse
    0.23
    Activations Density 1.073%

    No Known Activations