© 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. 140592
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Negative Logits
    ingly
    -0.31
    -quarter
    -0.28
    inda
    -0.27
    é¦ĸå¸Ń
    -0.25
    çĶŁæ®ĸ
    -0.24
    人éĢī
    -0.24
    æĬĬèĩªå·±
    -0.24
    Species
    -0.24
     transcend
    -0.24
    çļĦ身份
    -0.24
    POSITIVE LOGITS
     SUN
    0.27
     SOM
    0.26
    éĺ¿æĭī
    0.25
    ()'
    0.23
     som
    0.23
    stände
    0.23
    .sun
    0.23
    缮ãģ®
    0.23
    潺
    0.23
    Som
    0.23
    Activations Density 16.052%

    No Known Activations