© 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. 95242
    Prev
    Next
    INDEX
    Explanations

    research and 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
    Not in Any Lists

    No Comments

    Negative Logits
     report
    -0.27
    æĬ¥åijĬ
    -0.27
    ball
    -0.26
     onto
    -0.26
    report
    -0.26
    ptions
    -0.26
    acle
    -0.26
    åĬ¨çĶŁæĪIJ
    -0.25
    鸳
    -0.25
     пÑĥ
    -0.25
    POSITIVE LOGITS
    ritz
    0.31
     thẳng
    0.26
    æ°¢
    0.25
    ä¸ĢåŃĹ
    0.25
    æīĵæĭ¼
    0.25
    elapsed
    0.24
    brains
    0.24
    translations
    0.24
    éĻª
    0.24
    .op
    0.24
    Activations Density 0.883%

    No Known Activations