© 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. 50105
    Prev
    Next
    INDEX
    Explanations

    keys and values in structured data

    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
    lite
    -0.08
    å³
    -0.07
    æ±Łå®ģ
    -0.07
    æįį
    -0.07
    ulton
    -0.07
    íĥij
    -0.06
    åѦåľĴ
    -0.06
    åı¯æľĽ
    -0.06
    è¢ħ
    -0.06
     воз
    -0.06
    POSITIVE LOGITS
    为åħ¬åı¸
    0.08
    åľ¨åħ¬åı¸
    0.07
    çī¹å®ļ
    0.07
    æĺ¯åħ¬åı¸
    0.07
    ä¸ĢèĦļ
    0.07
    misc
    0.07
    æ³ķå®ļ
    0.07
    èħ³è¸ı
    0.07
    =>$
    0.07
    ä»»
    0.07
    Activations Density 0.020%

    No Known Activations