© 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. 32-TRANSCODER-HP
    7. 42638
    Prev
    Next
    INDEX
    Explanations

    Indian names and actors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĻļ
    -0.31
    åĨ²éĶĭ
    -0.27
    ç¨ĭ
    -0.26
     homosexuality
    -0.26
    nas
    -0.26
     race
    -0.26
    ho
    -0.25
    ä¼Ĺ
    -0.25
    个å¤ļå°ıæŶ
    -0.24
     horns
    -0.23
    POSITIVE LOGITS
    é¢Ĩ导
    0.32
    æį
    0.29
    lyph
    0.29
    ital
    0.28
     apl
    0.27
    åįıåĬŀ
    0.27
    uplic
    0.26
    -Le
    0.25
    è°ģ
    0.25
    [Math
    0.24
    Activations Density 0.004%

    No Known Activations