© 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. 24518
    Prev
    Next
    INDEX
    Explanations

    identifying

    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
    ç¨ĭå¼ı
    -0.29
    ç¨ĭ
    -0.27
    @Table
    -0.26
     iam
    -0.26
     Biom
    -0.26
    åIJī
    -0.24
    ikit
    -0.24
    第ä¸ĢåIJį
    -0.24
    ä¿¡
    -0.23
    æĤł
    -0.23
    POSITIVE LOGITS
    ãĢģ
    0.37
    ãĢģãĢĮ
    0.31
    ãĢģ↵↵
    0.28
    ãĢģ“
    0.28
    çļĦè¶ĭåĬ¿
    0.27
     nextProps
    0.26
    èĩ³æĸ¼
    0.25
    åĤ¾
    0.25
    .Screen
    0.25
     trending
    0.25
    Activations Density 0.003%

    No Known Activations