© 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. 14036
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    S
    -0.06
    oy
    -0.06
    pte
    -0.06
     List
    -0.05
    {}
    -0.05
    ↵
    -0.05
    rome
    -0.05
     ref
    -0.05
     B
    -0.05
    [/
    -0.05
    POSITIVE LOGITS
    æĪ´ç»´æĸ¯
    0.09
    (et
    0.09
    ukul
    0.09
    -License
    0.09
    aliser
    0.08
    åħ¬ä¼Ĺå¹³åı°
    0.08
    -Identifier
    0.08
    jata
    0.08
    ubl
    0.08
    åħ¨ç³»
    0.08
    Activations Density 0.019%

    No Known Activations