© 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. 58563
    Prev
    Next
    INDEX
    Explanations

    each

    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
    boo
    -0.26
     blow
    -0.26
    第äºĮ个
    -0.25
    busters
    -0.25
     Collections
    -0.25
    ::$
    -0.24
    _depend
    -0.24
    %/
    -0.24
    ·»
    -0.23
    yro
    -0.23
    POSITIVE LOGITS
     each
    0.92
    each
    0.90
    å½¼æѤ
    0.81
    Each
    0.80
     Each
    0.77
     elkaar
    0.74
     EACH
    0.71
    .each
    0.71
    (each
    0.69
    æ¯ı个
    0.66
    Activations Density 0.007%

    No Known Activations