© 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. 35-TRANSCODER-HP
    7. 40229
    Prev
    Next
    INDEX
    Explanations

    Citations or references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĽ´
    -0.38
     æĽ´
    -0.30
    çĹĤ
    -0.27
    arrera
    -0.25
    æĽ´å¿«
    -0.25
    å¹´éĻIJ
    -0.25
     daha
    -0.23
     quicker
    -0.23
    isin
    -0.23
    .dropdown
    -0.23
    POSITIVE LOGITS
    åIJĦ个æĸ¹éĿ¢
    0.26
     actual
    0.25
     official
    0.24
    è¿Ļ个éĹ®é¢ĺ
    0.24
     Kore
    0.23
     Moms
    0.23
     gegenüber
    0.23
    modern
    0.23
    åħ±éĿĴåĽ¢
    0.23
    åŃij
    0.23
    Activations Density 51.890%

    No Known Activations