© 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. 95281
    Prev
    Next
    INDEX
    Explanations

    Organization acronyms

    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
    Not in Any Lists

    No Comments

    Negative Logits
    å¥ĩ
    -0.35
    ervation
    -0.28
    Core
    -0.26
    itre
    -0.26
    anford
    -0.26
    -byte
    -0.25
    æŃ£åľ¨
    -0.25
     //</
    -0.25
    amodel
    -0.24
     agreed
    -0.24
    POSITIVE LOGITS
    æĽ´ä½İ
    0.30
    hyp
    0.28
     higher
    0.27
    higher
    0.27
    ä¸įåĩºæĿ¥
    0.26
    估计
    0.24
     emb
    0.24
    论
    0.24
     lower
    0.24
    æĽ´é«ĺ
    0.23
    Activations Density 0.883%

    No Known Activations