© 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. 9880
    Prev
    Next
    INDEX
    Explanations

    sentence terminators

    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
    rael
    -0.08
    jeÄį
    -0.07
    æ®ĭ
    -0.07
    á»ijn
    -0.07
    _suspend
    -0.07
    جاز
    -0.07
    æŀķ
    -0.07
     Neo
    -0.07
    åħ°çī¹
    -0.07
    idy
    -0.06
    POSITIVE LOGITS
    otta
    0.08
    ustra
    0.08
    æĺ¥èĬ±
    0.08
    ारà¥į
    0.07
    好åŃ©åŃIJ
    0.07
    ä½łçļĦçĶŁæ´»
    0.07
    åħĪåIJİåľ¨
    0.06
    ÑĥÑģÑĤа
    0.06
     ejac
    0.06
    ilha
    0.06
    Activations Density 0.003%

    No Known Activations