© 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. 41710
    Prev
    Next
    INDEX
    Explanations

    diagnostic criteria

    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
    å¹´çļĦæŶåĢĻ
    -0.07
    缮æłĩæĺ¯
    -0.07
    ä»»åĬ¡æĺ¯
    -0.07
    iling
    -0.07
    çŃĶæ¡Īæĺ¯
    -0.07
    çļĦæŃ¥ä¼IJ
    -0.07
    çļĦèĦ¸ä¸Ĭ
    -0.07
    æĸ¹æ³ķãģ¯
    -0.07
    çļĦ缮åħī
    -0.06
    çļĦæŶéĹ´éĩĮ
    -0.06
    POSITIVE LOGITS
     vs
    0.17
     versus
    0.16
    vs
    0.12
    æĺ¯æĢİæł·
    0.11
    çļĦçī¹çĤ¹
    0.11
    çļĦåħ·ä½ĵ
    0.11
    çļĦéĩįè¦ģæĢ§
    0.11
    æĺ¯å¦Ĥä½ķ
    0.11
    çļĦéĩįè¦ģæĦıä¹ī
    0.11
    为ä½ķ
    0.10
    Activations Density 0.062%

    No Known Activations