© 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. 24373
    Prev
    Next
    INDEX
    Explanations

    Winter

    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°ı
    -0.29
    塬
    -0.28
    ä¸ī级
    -0.26
    è¡Ģ
    -0.24
    .toObject
    -0.24
    èĥ¶åĽĬ
    -0.24
    	ROM
    -0.24
    cks
    -0.24
    assy
    -0.24
    æݧèĤ¡éĽĨåĽ¢
    -0.24
    POSITIVE LOGITS
    ing
    0.31
    boarding
    0.28
     mobility
    0.28
    -hot
    0.28
     indoor
    0.27
    ption
    0.26
    fare
    0.26
    less
    0.26
    ed
    0.26
    å¯ĴåĨ·
    0.26
    Activations Density 0.310%

    No Known Activations