© 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. 24840
    Prev
    Next
    INDEX
    Explanations

    Names

    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
     refresh
    -0.26
     Blazers
    -0.23
    -edge
    -0.22
    .best
    -0.22
     retro
    -0.22
     rapidly
    -0.21
    fusc
    -0.21
    é¦Ī
    -0.21
    *y
    -0.21
    olicy
    -0.21
    POSITIVE LOGITS
    abad
    0.26
    æŁľ
    0.25
    ä¸įè§ģ
    0.25
    ampa
    0.24
    chw
    0.24
    omic
    0.23
    ech
    0.23
    çķ¥æľī
    0.23
    STALL
    0.23
    ören
    0.23
    Activations Density 0.032%

    No Known Activations