© 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. 31-TRANSCODER-HP
    7. 18232
    Prev
    Next
    INDEX
    Explanations

    there

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     a
    -0.28
    (map
    -0.26
    ä¸Ģè¾Ĩ
    -0.24
    åı¯ä»¥
    -0.24
    ussen
    -0.24
    ä¸Ģ个
    -0.24
     another
    -0.24
    æķħäºĭ
    -0.24
    >>>
    -0.23
    åĽ¾
    -0.23
    POSITIVE LOGITS
    è¿ĺæĺ¯è¦ģ
    0.28
    æĪijè¿ĺæĺ¯
    0.27
    ä¾Ŀæ³ķ追究
    0.27
    åĬĽè¿ĺæĺ¯
    0.25
    红éħĴ
    0.24
     hope
    0.24
    æĥĩ
    0.24
    éĤĦæĺ¯
    0.23
    è¿ĺéľĢè¦ģ
    0.23
    bbc
    0.23
    Activations Density 0.285%

    No Known Activations