© 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. 40070
    Prev
    Next
    INDEX
    Explanations

    Patent application 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
    isl
    -0.29
    equal
    -0.28
    cpt
    -0.27
    edImage
    -0.27
    :,
    -0.26
     dearly
    -0.25
    ncy
    -0.25
    нÑĤ
    -0.25
    å¤ĸéĿ¢
    -0.25
     versa
    -0.25
    POSITIVE LOGITS
    ;line
    0.27
    arine
    0.26
     gez
    0.26
    èĪį
    0.26
    STER
    0.25
    æľ¬æĬ¥è®¯
    0.25
    sb
    0.25
     reve
    0.24
    \web
    0.24
    orie
    0.24
    Activations Density 0.428%

    No Known Activations