© 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. 19887
    Prev
    Next
    INDEX
    Explanations

    non-English

    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
    Negative Logits
    æIJ¬å®¶
    -0.30
    æĭĽåij¼
    -0.25
    ä¹ĭ声
    -0.25
     Tonight
    -0.24
    having
    -0.24
    ockets
    -0.24
     poses
    -0.24
     move
    -0.24
    erg
    -0.24
    Moves
    -0.23
    POSITIVE LOGITS
    ahi
    0.29
    ioni
    0.28
    æĺ¯éĿŀ
    0.26
    æĶ¾æīĭ
    0.25
    ascript
    0.25
    åĶĩ
    0.25
     Urdu
    0.24
    cta
    0.24
    amu
    0.24
    æĶ¾åħ¥
    0.24
    Activations Density 1.642%

    No Known Activations