© 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. 21237
    Prev
    Next
    INDEX
    Explanations

    cookies followed by to

    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
    furter
    -0.08
    eya
    -0.07
    _EXEC
    -0.07
    liner
    -0.07
    lina
    -0.07
    lings
    -0.07
    _hor
    -0.07
    bole
    -0.07
    zte
    -0.07
     Rico
    -0.07
    POSITIVE LOGITS
     Pilk
    0.07
    ÑģÑĤÑĢе
    0.07
    athe
    0.06
    æݨåĩºçļĦ
    0.06
    bland
    0.06
    AGE
    0.06
    媲
    0.06
    è¿Ļä¸ľè¥¿
    0.06
    没æľīåĬŀæ³ķ
    0.06
    彪
    0.06
    Activations Density 0.222%

    No Known Activations