© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 38874
    Prev
    Next
    INDEX
    Explanations

    numbers, punctuation, and specific english words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roud
    -0.08
    满
    -0.07
    indy
    -0.07
    èĶµ
    -0.07
    airo
    -0.07
    жев
    -0.07
    igre
    -0.07
    _operand
    -0.06
    imbang
    -0.06
    klä
    -0.06
    POSITIVE LOGITS
     simpl
    0.12
    åıªåī©ä¸ĭ
    0.12
    ç®ĢåĮĸ
    0.12
     simplify
    0.11
    ä»ĸåıª
    0.11
    åıªæĺ¾ç¤º
    0.11
    ä»ħåī©
    0.11
     eliminate
    0.11
     eliminates
    0.11
    åıªåī©
    0.10
    Activations Density 0.102%

    No Known Activations