© 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. 39972
    Prev
    Next
    INDEX
    Explanations

    moderated

    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
    解
    -0.26
    åĽ½éģĵ
    -0.25
    èĬ¸
    -0.25
    probe
    -0.25
     convo
    -0.25
    _dem
    -0.25
    antro
    -0.23
    apy
    -0.23
    licing
    -0.23
     probe
    -0.23
    POSITIVE LOGITS
    èµ
    0.27
    .rd
    0.25
    irez
    0.25
    ;top
    0.25
    vented
    0.24
    çļĦä¸Ģéĥ¨åĪĨ
    0.24
    é¢Ŀå¤ĸ
    0.24
    è¡Ļ
    0.24
    说çļĦæĺ¯
    0.24
    fill
    0.24
    Activations Density 0.177%

    No Known Activations