© 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. 38532
    Prev
    Next
    INDEX
    Explanations

    questions and descriptions

    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
    DataManager
    -0.28
     mattered
    -0.27
    ä¸įäºĪ
    -0.25
    atab
    -0.25
    attempt
    -0.25
     modifier
    -0.24
     vind
    -0.24
    èĭŀ
    -0.24
     territories
    -0.24
     temper
    -0.24
    POSITIVE LOGITS
    lesi
    0.28
    él
    0.28
    esi
    0.28
    bis
    0.27
    listed
    0.26
    cos
    0.26
    æ³³
    0.26
    peer
    0.26
    Å¡
    0.25
    zilla
    0.25
    Activations Density 47.305%

    No Known Activations