© 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. 24148
    Prev
    Next
    INDEX
    Explanations

    news

    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
     maxim
    -0.33
     Maxim
    -0.32
     maximizing
    -0.29
    æľĢ大çļĦ
    -0.27
     bran
    -0.25
    æĿ¡
    -0.25
     maximize
    -0.25
    ader
    -0.24
    !/
    -0.24
    çļĦæľĢ大
    -0.24
    POSITIVE LOGITS
    èħ¥
    0.28
    callee
    0.26
    *((
    0.25
     clich
    0.25
    mos
    0.25
     first
    0.25
    clr
    0.24
    èī¾æ»ĭçĹħ
    0.24
    对äºİæĪij们
    0.23
    mongoose
    0.23
    Activations Density 0.007%

    No Known Activations