© 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. 22832
    Prev
    Next
    INDEX
    Explanations

    solution work attempt

    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
    uwen
    -0.08
    uger
    -0.07
    onde
    -0.07
    reon
    -0.06
    åľ¨åħ¶ä¸Ń
    -0.06
    çī¹æĢ§çļĦ
    -0.06
     Kurd
    -0.06
    rones
    -0.06
    åĴķåĻľ
    -0.06
     slight
    -0.06
    POSITIVE LOGITS
    urette
    0.10
    æĢĿè·¯
    0.08
    æĢĿè·¯åĴĮ
    0.08
    _outline
    0.08
    tte
    0.08
    urin
    0.08
     rewritten
    0.08
    letes
    0.08
    /work
    0.07
    tere
    0.07
    Activations Density 0.002%

    No Known Activations