© 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. 20-TRANSCODER-HP
    7. 142454
    Prev
    Next
    INDEX
    Explanations

    urban

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mù
    -0.28
    游æĪıéĩĮçļĦ
    -0.27
    è§Ħå®ļçļĦ
    -0.26
    velle
    -0.26
    绣çŃ¹æİ¨è¿Ľ
    -0.25
    æĹ¶ä»£çļĦ
    -0.25
    .latest
    -0.25
    æľĢæĸ°çļĦ
    -0.25
    æ±Ĺæ°´
    -0.24
    ckett
    -0.24
    POSITIVE LOGITS
    batim
    0.28
    èĺħ
    0.27
    geh
    0.26
    .band
    0.24
     доÑģÑĤÑĥп
    0.24
     tighten
    0.24
    =true
    0.24
    ãĥIJãĥ³ãĥī
    0.24
    rink
    0.24
    appers
    0.23
    Activations Density 9.937%

    No Known Activations