© 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. 28776
    Prev
    Next
    INDEX
    Explanations

    abbreviations followed by punctuation

    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
    بÙĤ
    -0.07
    èĥ½åĬĽåĪĨæŀIJ
    -0.07
    endu
    -0.07
    OCA
    -0.07
    leneck
    -0.06
    tep
    -0.06
    itt
    -0.06
    fdc
    -0.06
    dain
    -0.06
    çĸ¼çĪ±
    -0.06
    POSITIVE LOGITS
    å°Ķé¡¿
    0.08
    sms
    0.07
    æ¯ĹéĤ»
    0.07
    ÙĪ
    0.07
    यर
    0.07
     mind
    0.07
    ä¸įç¦ģ
    0.07
    æĺ±
    0.06
    usb
    0.06
    osat
    0.06
    Activations Density 0.748%

    No Known Activations