© 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. 2264
    Prev
    Next
    INDEX
    Explanations

    genes and abbreviations

    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
    zan
    -0.06
    &
    -0.06
    HY
    -0.06
    å¹³åı°åĴĮ
    -0.06
    ç¥IJ
    -0.06
    View
    -0.06
     Provision
    -0.06
    _ib
    -0.06
    oke
    -0.06
    onen
    -0.05
    POSITIVE LOGITS
    éĩij森
    0.09
    apun
    0.08
    Ỽm
    0.08
    ngh
    0.08
    éĺ¿å§Ĩ
    0.08
    sic
    0.07
    Æ°á»Ŀ
    0.07
     Buffered
    0.07
    ega
    0.07
    achel
    0.07
    Activations Density 0.039%

    No Known Activations