© 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. 41363
    Prev
    Next
    INDEX
    Explanations

    many

    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
    è¶Ĭ好
    -0.31
    åIJĪ
    -0.27
    ORB
    -0.27
    İ·
    -0.27
    åIJŀ
    -0.26
    éħĮ
    -0.26
    ä»»æĦı
    -0.25
    ç«łç¨ĭ
    -0.24
    è¿
    -0.24
    便æĺ¯
    -0.24
    POSITIVE LOGITS
     much
    1.34
    much
    1.13
     Much
    1.06
    Much
    0.98
     MUCH
    0.96
     mucho
    0.91
     viel
    0.61
     beaucoup
    0.57
     veel
    0.39
     many
    0.36
    Activations Density 0.001%

    No Known Activations