© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 18122
    Prev
    Next
    INDEX
    Explanations

    wall

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    subpackage
    -0.29
    alytics
    -0.29
    åIJ¸
    -0.28
    Ê°
    -0.27
    æİĪ
    -0.27
     waged
    -0.26
     asiat
    -0.25
    gypt
    -0.25
     Homeland
    -0.25
    ATED
    -0.25
    POSITIVE LOGITS
     opposite
    0.35
    建çŃijæĿIJæĸĻ
    0.29
     construction
    0.28
    æīĵéĢłåĩº
    0.28
    builders
    0.28
     builders
    0.27
     contrasting
    0.27
     entirely
    0.27
    åħ¨éĿ¢å»ºæĪIJ
    0.27
     constructed
    0.26
    Activations Density 0.876%

    No Known Activations