© 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. 32062
    Prev
    Next
    INDEX
    Explanations

    true or false

    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
    inston
    -0.09
    yles
    -0.08
    ingen
    -0.08
    ä¿Ĺè¯Ŀ说
    -0.08
    åĮħ饺åŃIJ
    -0.08
    áĥĶáĥĵ
    -0.07
    ÚĨÙĩ
    -0.07
    伤å¿ĥ
    -0.07
    åĭ¤ä¿ŃèĬĤ约
    -0.07
    常åIJĥ
    -0.07
    POSITIVE LOGITS
    opsis
    0.06
    åIJİèĢħ
    0.06
    ND
    0.06
    ä¸į
    0.06
     judgments
    0.06
    交äºĴ
    0.06
    æIJŀç¬ij
    0.05
    表çĻ½
    0.05
    åĪ¤
    0.05
    Assignable
    0.05
    Activations Density 0.003%

    No Known Activations