© 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. 96787
    Prev
    Next
    INDEX
    Explanations

    peace

    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
    roud
    -0.28
    åĿļæĮģä¸įæĩĪ
    -0.28
     clever
    -0.27
    æģŃæķ¬
    -0.27
    è¯ļå®ŀ
    -0.27
    æĢĴ
    -0.26
    èĢIJå¿ĥ
    -0.26
     peaceful
    -0.26
    peace
    -0.26
    ä¼ļè§īå¾Ĺ
    -0.26
    POSITIVE LOGITS
    uckets
    0.34
     of
    0.30
    eps
    0.28
     Omega
    0.28
    _of
    0.27
    opia
    0.27
     Of
    0.27
    éģŃéģĩ
    0.27
    full
    0.27
    æ·±
    0.27
    Activations Density 0.109%

    No Known Activations