© 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. 61490
    Prev
    Next
    INDEX
    Explanations

    time-st

    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
    æļĩ
    -0.09
    omar
    -0.08
    Camp
    -0.07
    ENC
    -0.07
    iap
    -0.07
    ¯¯¯¯
    -0.07
    _TA
    -0.07
    ÙĦÙĬÙĩ
    -0.07
     squeez
    -0.07
    reiber
    -0.07
    POSITIVE LOGITS
    æī¾ä¸įåĪ°
    0.09
    ç»ıæŁ¥
    0.07
    utra
    0.07
     cari
    0.07
    .toLocale
    0.06
     impossible
    0.06
     Hermann
    0.06
    aret
    0.06
    æĹłå¤Ħ
    0.06
    è¿Ļå°±è¦ģæ±Ĥ
    0.06
    Activations Density 0.095%

    No Known Activations