© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 95838
    Prev
    Next
    INDEX
    Explanations

    Technical document snippets

    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
     Henrik
    -0.26
     feeling
    -0.25
    ::-
    -0.25
     LATIN
    -0.25
    okino
    -0.25
    æĶ¹æĪIJ
    -0.25
    .pm
    -0.24
    éĺı
    -0.24
    EXPORT
    -0.24
     beyond
    -0.23
    POSITIVE LOGITS
    aint
    0.28
    æ¢ĥ
    0.28
    ince
    0.25
    ät
    0.25
    交å¾Ģ
    0.24
    developer
    0.24
    ant
    0.24
    æĮ£æīİ
    0.24
    é¢ģå¥ĸ
    0.24
    ytt
    0.24
    Activations Density 0.003%

    No Known Activations