© 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. 33971
    Prev
    Next
    INDEX
    Explanations

    train names and numbers

    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
    å°ĺ
    -0.09
    ä¿ĥ
    -0.08
    对å¾ħ
    -0.08
    åİ®
    -0.07
    raÄĩ
    -0.07
    è¡·
    -0.07
    æĿIJ
    -0.07
    chet
    -0.06
    ç¨į
    -0.06
    äºŁå¾ħ
    -0.06
    POSITIVE LOGITS
    .connect
    0.07
    åĽŀç¨ĭ
    0.07
    å»ī
    0.07
    StringLength
    0.07
    abase
    0.07
    åĩºåıij
    0.07
    çµĮçĶ±
    0.07
    ours
    0.07
    æľ¬å¸ĸ
    0.07
    avez
    0.07
    Activations Density 0.016%

    No Known Activations