© 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. 23900
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
    frame
    -0.30
    /frame
    -0.26
    ilio
    -0.26
    ardi
    -0.26
    覺
    -0.25
    ogenic
    -0.25
    _eval
    -0.24
    è¢Ħ
    -0.24
    _prop
    -0.24
    æĹ¥æĻļéĹ´
    -0.24
    POSITIVE LOGITS
    çľĭçľĭ
    0.27
    æµģè¡ĮçļĦ
    0.26
    缩å°ı
    0.25
     governments
    0.25
    æµģè¡Į
    0.24
    elts
    0.24
    bris
    0.24
    _ERRORS
    0.24
    erten
    0.24
     punishing
    0.24
    Activations Density 0.007%

    No Known Activations