© 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. 35-TRANSCODER-HP
    7. 38805
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    инг
    -0.26
     washer
    -0.25
    å¼Ģæľº
    -0.25
     Ritch
    -0.25
    ToEnd
    -0.25
    -runtime
    -0.25
     Locker
    -0.24
     Jonah
    -0.24
     caches
    -0.24
    åķ®
    -0.24
    POSITIVE LOGITS
    gue
    0.30
    ru
    0.30
    gu
    0.29
    erta
    0.29
    bes
    0.27
    ku
    0.27
    åºı
    0.27
    ERT
    0.27
    remove
    0.27
    hes
    0.27
    Activations Density 1.241%

    No Known Activations