© 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. 40462
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    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
     acknow
    -0.26
    èĢĻ
    -0.25
    ooks
    -0.25
    çĸı导
    -0.24
    overrides
    -0.24
    工夫
    -0.24
    åįĥæĸ¹çĻ¾è®¡
    -0.24
     matter
    -0.24
     corros
    -0.23
    ä¸ĩäºĭ
    -0.23
    POSITIVE LOGITS
     leaf
    0.26
     baj
    0.26
    åŃ©
    0.24
    管çIJĨæĿ¡ä¾ĭ
    0.24
    æľī趣çļĦ
    0.23
    ynchronously
    0.23
    é¢Ĩ
    0.23
    æľīæĦıæĢĿçļĦ
    0.23
     sub
    0.23
    uvo
    0.23
    Activations Density 0.225%

    No Known Activations