© 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. 10430
    Prev
    Next
    INDEX
    Explanations

    deriving equations and rules

    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
    è¿Ļæł·çļĦéĹ®é¢ĺ
    -0.07
    entes
    -0.07
    onna
    -0.07
    chal
    -0.07
    æµ·ä¸ľ
    -0.06
    ä¸ij
    -0.06
    æīĵ好
    -0.06
    exual
    -0.06
     Cham
    -0.06
    åŁºæķ°
    -0.06
    POSITIVE LOGITS
     extracted
    0.11
     daraus
    0.09
     resulting
    0.09
    extract
    0.09
     Extract
    0.09
    Extract
    0.09
    æıIJåıĸ
    0.09
     resultant
    0.09
     extract
    0.09
     extracting
    0.08
    Activations Density 0.021%

    No Known Activations