© 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. 11543
    Prev
    Next
    INDEX
    Explanations

    interface contract/implementation

    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
    çĶµæ°Ķå·¥ç¨ĭ
    -0.08
    chst
    -0.08
    estre
    -0.08
    POCH
    -0.08
    WISE
    -0.08
    idenza
    -0.08
    è¿ĻäºĽåĽłç´ł
    -0.07
    èĥŃ
    -0.07
    urma
    -0.07
    -vars
    -0.07
    POSITIVE LOGITS
     interfaces
    0.09
    æİ¥åı£
    0.09
     interface
    0.09
     iface
    0.09
    å±¥è¡Į
    0.08
     API
    0.08
    è¦ģæ±Ĥ
    0.08
    çļĦåŁºæľ¬è¦ģæ±Ĥ
    0.08
     duck
    0.08
    çļĦè¦ģæ±Ĥ
    0.08
    Activations Density 0.277%

    No Known Activations