© 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. 41190
    Prev
    Next
    INDEX
    Explanations

    URLs and code

    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
    setQuery
    -0.30
    enan
    -0.27
    andler
    -0.27
    åı»
    -0.26
    ä¸ĩåIJį
    -0.25
     verdiÄŁi
    -0.25
    quÃŃ
    -0.25
    鲫
    -0.25
    oston
    -0.25
    Premium
    -0.24
    POSITIVE LOGITS
    fat
    0.32
    æĹ¢
    0.28
    langs
    0.27
    CC
    0.27
    ilia
    0.27
    raise
    0.27
    ais
    0.26
    altern
    0.26
    th
    0.25
     fat
    0.25
    Activations Density 0.925%

    No Known Activations