© 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. 20-TRANSCODER-HP
    7. 129268
    Prev
    Next
    INDEX
    Explanations

    virus subtypes and serotypes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    缩
    -0.30
    iola
    -0.28
     shrink
    -0.26
    latex
    -0.25
     reportedly
    -0.25
    ä¼Łå¤§çļĦ
    -0.24
    縮
    -0.24
    å½ķ
    -0.24
     Corpus
    -0.23
    å½ĵåľ°çļĦ
    -0.23
    POSITIVE LOGITS
    nı
    0.26
    quets
    0.25
    ä¸įä¸Ģæł·
    0.25
    ãĤ·ãĥ£ãĥ«
    0.24
    emale
    0.24
    对åħ¬åı¸
    0.24
    INDER
    0.24
    -quarter
    0.23
    ãĥĭãĥĥãĤ¯
    0.23
    .throw
    0.23
    Activations Density 3.404%

    No Known Activations