© 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. 40214
    Prev
    Next
    INDEX
    Explanations

    Fra

    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
     advertisement
    -0.28
     blinked
    -0.27
     adjoining
    -0.27
    çĥŁçģ«
    -0.26
     spotting
    -0.26
    åħ¨åªĴä½ĵ
    -0.26
    æķ°çłģ
    -0.26
     driveway
    -0.25
     cocktail
    -0.25
    inform
    -0.25
    POSITIVE LOGITS
    us
    0.32
    zenia
    0.29
    uno
    0.28
    že
    0.27
    zc
    0.27
    pez
    0.27
    zial
    0.27
     cz
    0.27
    ük
    0.27
    ushing
    0.26
    Activations Density 1.161%

    No Known Activations