© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26754
    Prev
    Next
    INDEX
    Explanations

    numbers and names

    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
    åıįåĢĴ
    -0.08
    ucat
    -0.07
    جÙĨ
    -0.07
    intl
    -0.07
    íģIJ
    -0.07
    acor
    -0.07
    ohan
    -0.07
    itera
    -0.07
    ctica
    -0.07
    mpi
    -0.07
    POSITIVE LOGITS
    æ±ŁåŁİ
    0.07
    enburg
    0.06
    æıIJåĩºè¦ģæ±Ĥ
    0.06
    躬
    0.06
    æľ¬ç½ij
    0.06
    дин
    0.06
    lh
    0.06
     bargain
    0.06
    ÅĽÄĩ
    0.06
    åĪĨ享åĪ°
    0.06
    Activations Density 0.023%

    No Known Activations