© 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. 95111
    Prev
    Next
    INDEX
    Explanations

    App

    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
    Negative Logits
    æ·¡
    -0.28
     ban
    -0.27
    ç¦ģ
    -0.26
    èĬĻèĵī
    -0.26
    ÙģÙĥ
    -0.25
     RN
    -0.25
    èµ°å»Ĭ
    -0.24
    å®ĺåı¸
    -0.24
    æ±
    -0.23
    MSN
    -0.23
    POSITIVE LOGITS
     app
    0.30
    rie
    0.29
    appoint
    0.28
    说å¾Ĺ
    0.28
    app
    0.27
     App
    0.27
    App
    0.26
     appId
    0.25
    	app
    0.25
    borg
    0.25
    Activations Density 0.019%

    No Known Activations