© 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. 40379
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    åĪĨæķ°çº¿
    -0.29
    é¢ľ
    -0.26
    -season
    -0.26
    ä¸Ģä¸ĸ
    -0.26
    åįĬ个
    -0.25
    _PERCENT
    -0.25
    ä¸īåĪĨä¹ĭä¸Ģ
    -0.25
    projects
    -0.25
     tackled
    -0.24
    å·¥ç¨ĭæĸ½å·¥
    -0.24
    POSITIVE LOGITS
    riad
    0.31
    enic
    0.26
    omatic
    0.26
     autob
    0.25
     <<<
    0.25
    ToDevice
    0.25
    .pair
    0.24
    .sha
    0.24
    ·»
    0.23
    nung
    0.23
    Activations Density 0.796%

    No Known Activations