© 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. 39491
    Prev
    Next
    INDEX
    Explanations

    applying patterns like vendor file system recurrence membrane absence

    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
    udge
    -0.08
    geld
    -0.08
    æľīåĩł
    -0.07
    ×ķ׳×Ķ
    -0.07
    xit
    -0.07
    fore
    -0.07
    á»Ĺ
    -0.07
    å©¢
    -0.07
    åħ°çī¹
    -0.07
    weis
    -0.07
    POSITIVE LOGITS
    天çĦ¶çļĦ
    0.10
    çļĦèĩªçĦ¶
    0.09
    天çĦ¶
    0.08
    åĽłåľ°
    0.08
    æ°´ä¸ŃçļĦ
    0.07
     Watkins
    0.07
     naturally
    0.07
    å¤©çľŁ
    0.07
    èĩªçĦ¶çļĦ
    0.07
     due
    0.07
    Activations Density 0.110%

    No Known Activations