© 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. 23591
    Prev
    Next
    INDEX
    Explanations

    changes and states

    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
     Brewer
    -0.07
    åįĥåįĥä¸ĩ
    -0.07
    åīį款
    -0.07
    åı¦å¤ĸä¸Ģç§į
    -0.06
    æĪij并ä¸į
    -0.06
    itters
    -0.06
    åIJİè¿Ľ
    -0.06
    ŀ
    -0.06
    è¿ĺæľīä¸Ģç§į
    -0.06
    éĢŁ
    -0.06
    POSITIVE LOGITS
    æı
    0.10
    å¤įåĪ¶æĪĸ
    0.08
    å·įå·į
    0.08
     cioè
    0.08
    åħ¶æŀĹ
    0.08
    igne
    0.07
    pires
    0.07
    aira
    0.07
    hamster
    0.07
     gla
    0.07
    Activations Density 0.459%

    No Known Activations