© 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. 56714
    Prev
    Next
    INDEX
    Explanations

    Code or technical documents

    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
    Not in Any Lists

    No Comments

    Negative Logits
     kiếm
    -0.29
    Y
    -0.28
     unilateral
    -0.27
    idd
    -0.27
    laps
    -0.26
    Xi
    -0.26
    æľĪ以æĿ¥
    -0.26
    iveness
    -0.25
    X
    -0.25
    æIJ¬
    -0.25
    POSITIVE LOGITS
     Moz
    0.28
    setQuery
    0.27
    éļĨ
    0.27
     Bentley
    0.26
    lift
    0.26
    PED
    0.25
     JIT
    0.24
    éĵ
    0.24
     tqdm
    0.24
    gel
    0.24
    Activations Density 0.020%

    No Known Activations