© 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. 41180
    Prev
    Next
    INDEX
    Explanations

    whether true or applies

    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
    Å¡an
    -0.08
    æĹłäºĭ
    -0.07
    cese
    -0.07
    edur
    -0.06
    è¨ĵ
    -0.06
    ä¹ħçļĦ
    -0.06
    ÙĪا
    -0.06
    éªĭ
    -0.06
    æĹłæķħ
    -0.06
    оби
    -0.06
    POSITIVE LOGITS
    å°¤åħ¶
    0.11
    å°¤åħ¶åľ¨
    0.10
    éĢĤçĶ¨äºİ
    0.10
    å½ĵä»ĸ
    0.09
    ä¸įéĻIJäºİ
    0.09
    éĢĤçĶ¨èĮĥåĽ´
    0.09
     applies
    0.08
     aplica
    0.08
     اÙĦØŃاÙĦ
    0.08
     geldt
    0.08
    Activations Density 0.590%

    No Known Activations