© 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. 41184
    Prev
    Next
    INDEX
    Explanations

    rust/čč

    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
    yst
    -0.32
    é£İ湿
    -0.30
    LAT
    -0.26
    olics
    -0.24
    飧æĢ§
    -0.24
    .characters
    -0.24
    fab
    -0.24
     Manila
    -0.23
    оÐ
    -0.23
     lows
    -0.23
    POSITIVE LOGITS
    觳
    0.30
    quir
    0.30
    arez
    0.27
    羣çĪ±
    0.26
     errorThrown
    0.26
    åĭ¤
    0.26
     beet
    0.25
    iston
    0.24
    utation
    0.24
     halted
    0.24
    Activations Density 1.095%

    No Known Activations