© 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. 1778
    Prev
    Next
    INDEX
    Explanations

    V(P,Q,n) function recurrence

    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
    æĹĹé¼ĵ
    -0.07
    immun
    -0.07
    leur
    -0.06
    ambar
    -0.06
    thy
    -0.06
    æĸ°åįİ社记èĢħ
    -0.06
    fica
    -0.06
    ascii
    -0.06
    unte
    -0.06
    olim
    -0.06
    POSITIVE LOGITS
    aÅĤ
    0.08
    ofs
    0.08
    ussen
    0.08
    éĿĴå·ŀ
    0.07
     otherwise
    0.07
    裳
    0.07
    å½ĵ羣
    0.07
    URA
    0.07
     outs
    0.07
    orts
    0.06
    Activations Density 0.049%

    No Known Activations