© 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. 23-TRANSCODER-HP
    7. 24669
    Prev
    Next
    INDEX
    Explanations

    library

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è´£ç¼ĸ
    -0.28
    åģļ梦
    -0.28
    åıįè¿ĩæĿ¥
    -0.27
    ady
    -0.27
    éĩİå¿ĥ
    -0.26
    ç«¥è£ħ
    -0.25
    èĩ¾
    -0.25
     convers
    -0.24
    ther
    -0.24
    itus
    -0.24
    POSITIVE LOGITS
    s
    0.45
    scape
    0.35
    æĪ¿
    0.28
    ra
    0.28
     hall
    0.28
    raries
    0.28
    hof
    0.27
    space
    0.26
    fuse
    0.25
    as
    0.25
    Activations Density 0.037%

    No Known Activations