© 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. 30-TRANSCODER-HP
    7. 97073
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ãģĭãģijãģ¦
    -0.26
    ç½ijç«Ļ
    -0.26
    ä¸ĩ象
    -0.26
    æĮ½
    -0.26
    glob
    -0.26
    _OBJ
    -0.25
    ingers
    -0.25
    URT
    -0.25
    ç¾Į
    -0.24
    èµĤ
    -0.24
    POSITIVE LOGITS
     forty
    0.31
    åĨľ
    0.31
     nineteen
    0.30
     twenty
    0.30
     fifty
    0.30
     ten
    0.29
     eighteen
    0.28
     seventeen
    0.28
     ninety
    0.28
     thirty
    0.28
    Activations Density 0.886%

    No Known Activations