© 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. 58271
    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_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
    æĢ»éĩı
    -0.26
    arious
    -0.26
    sov
    -0.26
    ä¸ŃåĽ½å¸Ĥåľº
    -0.25
    REAK
    -0.25
    atab
    -0.25
     Jennings
    -0.25
    <boost
    -0.25
     provisional
    -0.24
    *out
    -0.24
    POSITIVE LOGITS
    uhe
    0.27
    :M
    0.25
    å¦Ĥä¸ĭ
    0.25
    icles
    0.25
     abbrev
    0.24
    ãĤªãĥ¼
    0.24
     FREE
    0.23
    te
    0.23
    æĺ¶
    0.23
    èģĮ称
    0.23
    Activations Density 0.002%

    No Known Activations