© 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. 40370
    Prev
    Next
    INDEX
    Explanations

    send

    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
    èĥ½åIJ¦
    -0.32
     whether
    -0.29
    itors
    -0.27
    æĺ¯åIJ¦ä¼ļ
    -0.27
    èĥ½ä¸įèĥ½
    -0.26
    utsch
    -0.26
    æĺ¯åIJ¦
    -0.26
    举
    -0.26
    åѦèĢħ
    -0.26
    bool
    -0.25
    POSITIVE LOGITS
    -automatic
    0.27
     LETTER
    0.26
    æºľ
    0.25
    -enter
    0.24
    ä¸ĢæŃ¥æŃ¥
    0.24
    ");//
    0.24
    isque
    0.24
    egin
    0.24
    kie
    0.24
    -done
    0.24
    Activations Density 0.204%

    No Known Activations