© 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. 37837
    Prev
    Next
    INDEX
    Explanations

    data, files, and reports

    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
    imeo
    -0.07
     lawmaker
    -0.07
    æľĢä½İåѦåİĨ
    -0.07
    æĬĬéĤ£
    -0.07
    å°ĨéĤ£
    -0.07
    ezen
    -0.07
    -note
    -0.07
    rvat
    -0.07
     Aussie
    -0.06
    ritel
    -0.06
    POSITIVE LOGITS
    ahir
    0.08
    aszt
    0.07
    å¸ĥæŀĹ
    0.07
     PhÆ°á»Ľc
    0.07
    ily
    0.07
    æĥħåĨµåıĬ
    0.07
    æĥħåĨµçļĦ
    0.06
    opal
    0.06
    æĥħåĨµåĪĨæŀIJ
    0.06
    alang
    0.06
    Activations Density 0.002%

    No Known Activations