© 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. 18-TRANSCODER-HP
    7. 88307
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    é¹Ħ
    -0.27
    dì
    -0.24
    _band
    -0.24
    èĺĸ
    -0.24
     research
    -0.24
     incorporating
    -0.24
    好åIJĹ
    -0.23
    velle
    -0.23
    ĽĦ
    -0.23
    .bundle
    -0.23
    POSITIVE LOGITS
    é¢ł
    0.25
    åĴĸ
    0.25
    staff
    0.25
     hairs
    0.24
     bleiben
    0.23
    åĸĢ
    0.23
    ERP
    0.23
    UBL
    0.23
    æµģæ·Į
    0.23
    éĹ´éļĻ
    0.23
    Activations Density 0.167%

    No Known Activations