© 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. 51725
    Prev
    Next
    INDEX
    Explanations

    CST timezones

    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
    æĸ¯é¡¿
    -0.07
    egn
    -0.07
     Bundy
    -0.07
     ÐŀÑģно
    -0.07
     Richardson
    -0.07
    åħĭèݱ
    -0.07
    åħ´å®ī
    -0.06
    abas
    -0.06
    igur
    -0.06
     lond
    -0.06
    POSITIVE LOGITS
    cha
    0.08
    |i
    0.07
    ÙĪار
    0.07
    æ®Ĭ
    0.07
    æľŁä¸Ń
    0.06
    çĪ¬åĪ°
    0.06
    ãĥĩãĤ¤
    0.06
    à¸ŀรรà¸ĵ
    0.06
    chs
    0.06
    çĴĭ
    0.06
    Activations Density 0.001%

    No Known Activations