© 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. 9917
    Prev
    Next
    INDEX
    Explanations

    missing

    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
    umes
    -0.28
    assed
    -0.24
    oref
    -0.24
    ulton
    -0.24
    baugh
    -0.24
    untu
    -0.23
    社ä¼ļåĮĸ
    -0.23
     Fet
    -0.23
     lul
    -0.23
    åįļæĸĩ
    -0.23
    POSITIVE LOGITS
     missing
    1.04
     disappeared
    0.98
     disappear
    0.94
    æ¶Ī失
    0.90
    missing
    0.88
     Missing
    0.86
     disappearance
    0.86
    Missing
    0.85
     disappears
    0.85
     vanished
    0.83
    Activations Density 0.022%

    No Known Activations