© 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. 50804
    Prev
    Next
    INDEX
    Explanations

    package/which/what question

    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
    ipto
    -0.07
    ä¸Ģ线
    -0.06
    ÏĢο
    -0.06
    ng
    -0.06
    atr
    -0.06
    rev
    -0.06
    agul
    -0.06
    iese
    -0.06
    agram
    -0.06
    mo
    -0.06
    POSITIVE LOGITS
    çļĦåıijå±ķåĴĮ
    0.08
    codegen
    0.07
    åĮ£
    0.07
    cliffe
    0.07
    è·Ľ
    0.07
    lify
    0.07
    ìĸ´ë¯¼
    0.07
    اÛĮÛĮ
    0.07
    body
    0.07
    çĶĦ
    0.07
    Activations Density 0.003%

    No Known Activations