© 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. 61504
    Prev
    Next
    INDEX
    Explanations

    links and articles

    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
    alat
    -0.10
     INFORMA
    -0.09
    æĪijçļĦ书æŀ¶
    -0.08
    ubber
    -0.08
    åĨ³ä¸į
    -0.08
    ç¼ĸè¾ijäºİ
    -0.08
    ellige
    -0.08
     koll
    -0.08
    æĹłæīĢè°ĵ
    -0.08
    eon
    -0.08
    POSITIVE LOGITS
    ç¯ĩä¸Ģ
    0.07
    æ±ŁåŁİ
    0.07
    åħīéĺ´
    0.06
    èĮĥæĸĩ
    0.06
     below
    0.06
     unl
    0.06
    æįī
    0.06
    www
    0.06
    æĦŁäººçļĦ
    0.06
    amos
    0.06
    Activations Density 0.012%

    No Known Activations