© 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. 18088
    Prev
    Next
    INDEX
    Explanations

    ections

    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
    aten
    -0.29
    ä¸įèµ·
    -0.28
    bs
    -0.26
    æ»ĵ
    -0.26
    ä¸įäºĨ解
    -0.25
    éĩľ
    -0.25
    è±¹
    -0.25
    è´¸
    -0.25
    çļĦæł·åŃIJ
    -0.24
    айн
    -0.24
    POSITIVE LOGITS
    'clock
    0.25
    欤
    0.25
    allel
    0.25
    ãģłãģ£ãģŁ
    0.24
    ãĤĵãģłãĤįãģĨ
    0.24
    ché
    0.24
     Trem
    0.24
    ãģĤãģ£ãģŁ
    0.24
    æı®
    0.23
    ierce
    0.23
    Activations Density 1.643%

    No Known Activations