© 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. 38379
    Prev
    Next
    INDEX
    Explanations

    reported findings

    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
    æĭ¥
    -0.07
    ÛĮÙħاÙĨ
    -0.07
    æĪijçŁ¥éģĵ
    -0.06
    quil
    -0.06
    Bloc
    -0.06
    ival
    -0.06
    为æĪij们çļĦ
    -0.06
    £¼
    -0.06
    æĪij们æŃ£åľ¨
    -0.06
    åı³
    -0.06
    POSITIVE LOGITS
    å½ĵæŶçļĦ
    0.10
    å½ĵæŶ
    0.09
     unpublished
    0.08
    好åĥıæĺ¯
    0.08
    pta
    0.08
     reportedly
    0.08
    æĭ³éģĵ
    0.08
    åIJĮå¹´
    0.08
     reported
    0.08
    çķ¶æĻĤ
    0.08
    Activations Density 0.338%

    No Known Activations