© 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. 97018
    Prev
    Next
    INDEX
    Explanations

    code, foreign text, names

    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
    æ´ª
    -0.31
    _pins
    -0.27
    æİ¢
    -0.27
    samp
    -0.25
    åºij
    -0.25
    Sphere
    -0.24
     scho
    -0.24
    ä¿ĿæĮģ
    -0.24
    èĤ¢
    -0.23
    txn
    -0.23
    POSITIVE LOGITS
    顺
    0.43
    康çĨĻ
    0.36
     sevent
    0.33
    éĺī
    0.32
    éłĨ
    0.31
     Bar
    0.31
    çı°
    0.30
    Closure
    0.29
    æIJĶ
    0.28
     bar
    0.28
    Activations Density 0.891%

    No Known Activations