© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63130
    Prev
    Next
    INDEX
    Explanations

    pre-granulation, deacetylation, phosphorylation

    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
    paque
    -0.09
    -0.08
    ãĥ¼ãĤº
    -0.08
    ãĥ¼ãĤ«ãĥ¼
    -0.07
    lerce
    -0.07
     Ended
    -0.07
    ási
    -0.07
    åĴĮæĹ¥æľ¬
    -0.07
    大åı¯
    -0.07
    ार
    -0.06
    POSITIVE LOGITS
    ugen
    0.09
    uent
    0.08
    iche
    0.08
    lessness
    0.08
    éļ¾çļĦ
    0.08
    uré
    0.08
    urat
    0.07
    ulent
    0.07
    éĴ¦
    0.07
    anch
    0.07
    Activations Density 0.004%

    No Known Activations