© 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. 39829
    Prev
    Next
    INDEX
    Explanations

    Lie

    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
    è¡£
    -0.28
    §è¡Į
    -0.27
    ivals
    -0.27
     mane
    -0.27
    umo
    -0.26
     Made
    -0.25
    icles
    -0.25
     nữa
    -0.25
    ivre
    -0.24
    _FD
    -0.24
    POSITIVE LOGITS
    _BEGIN
    0.26
    istan
    0.24
    _begin
    0.24
    bare
    0.23
    closest
    0.23
    ä¸ĭçļĦ
    0.23
    hä
    0.23
    åĽ½å®¶éĺŁ
    0.23
    bench
    0.23
    _personal
    0.23
    Activations Density 0.112%

    No Known Activations