© 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. 27-TRANSCODER-HP
    7. 7910
    Prev
    Next
    INDEX
    Explanations

    disasters and geology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä¿Ŀå®ī
    -0.28
    Hel
    -0.27
    æĵ¾
    -0.26
     heaps
    -0.26
    _Global
    -0.25
     nave
    -0.25
    _defs
    -0.25
    éģ®
    -0.24
    ç³»
    -0.23
     exe
    -0.23
    POSITIVE LOGITS
    æĿ¿åĿĹ
    0.32
    æĿ¿
    0.31
     plate
    0.28
     plates
    0.28
    itzer
    0.28
    rod
    0.27
    èĩªé©¾
    0.27
    orida
    0.26
     Masters
    0.26
    rupt
    0.26
    Activations Density 0.008%

    No Known Activations