© 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. 40779
    Prev
    Next
    INDEX
    Explanations

    population

    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
     Dro
    -0.29
    çļĦæ¶Īæģ¯
    -0.28
    çļĦæł·åŃIJ
    -0.28
    iday
    -0.27
    ä¸ĵéŨ
    -0.26
     Tin
    -0.26
    满足
    -0.26
    ;height
    -0.26
    cate
    -0.25
    é«ĺåĵģè´¨
    -0.25
    POSITIVE LOGITS
    碴
    0.27
    ï¼Įé»ĺ认
    0.27
    lijke
    0.25
    çł´
    0.25
    ARIO
    0.24
     Ahead
    0.24
     containerView
    0.24
     tú
    0.24
    orts
    0.24
    anie
    0.24
    Activations Density 1.136%

    No Known Activations