© 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. 63639
    Prev
    Next
    INDEX
    Explanations

    prior art or constitutes

    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
    ä¾į
    -0.07
    ptype
    -0.07
    为éļ¾
    -0.07
    Samples
    -0.07
    اط
    -0.07
    ä¸ĭæ°´
    -0.07
    å°ıéĿĴ
    -0.07
     potr
    -0.06
    andle
    -0.06
    _aliases
    -0.06
    POSITIVE LOGITS
    çIJ³å¨ľ
    0.08
    æ´ģ
    0.07
     ato
    0.07
     Äįe
    0.07
    lett
    0.07
    åħĥåĻ¨ä»¶
    0.06
    æ¦
    0.06
     Aspe
    0.06
    æĹ
    0.06
    é¡¹çĽ®æī¿åĬŀåįķä½į
    0.06
    Activations Density 0.039%

    No Known Activations