© 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. 38300
    Prev
    Next
    INDEX
    Explanations

    `basename` or `rows` and `words`

    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
    ç§įçļĦ
    -0.08
    èļ£
    -0.08
    çIJ²
    -0.08
    åľ°çIJĨä½įç½®ä¼ĺè¶Ĭ
    -0.07
    ạnh
    -0.07
    /gpl
    -0.07
     اÙĦشرÙĬÙģ
    -0.07
    ijken
    -0.07
    éļıçĿĢå¹´é¾Ħ
    -0.07
     eBook
    -0.07
    POSITIVE LOGITS
    itt
    0.08
    tt
    0.07
    æ´»åĬ¨çŃī
    0.07
    TP
    0.07
    ITT
    0.06
    ESA
    0.06
    dl
    0.06
    ittest
    0.06
    xb
    0.06
    æĬķ
    0.06
    Activations Density 0.014%

    No Known Activations