© 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. 43158
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æ¼Ĥ
    -0.29
    wy
    -0.29
    å©Ĩå©Ĩ
    -0.27
    Sense
    -0.25
    ç²¾ç¥ŀ
    -0.25
    åľ¨è·¯ä¸Ĭ
    -0.24
    sense
    -0.24
    .radians
    -0.24
     sense
    -0.24
     dep
    -0.24
    POSITIVE LOGITS
    èĦı
    0.31
    Łèĥ½
    0.27
    åıįä¹ĭ
    0.26
    *A
    0.24
    åĨ¶
    0.24
    éĢģæĿ¥
    0.24
    èĩªä»İ
    0.23
    ursion
    0.23
    nav
    0.23
    Administration
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.