© 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. 50317
    Prev
    Next
    INDEX
    Explanations

    father or founder of

    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¿ĥæĥĬ
    -0.09
    æī¿è¯º
    -0.07
    illi
    -0.07
    å¦ĤæľŁ
    -0.07
     relay
    -0.07
    relay
    -0.07
    alled
    -0.07
    è¿ĻåŃ©åŃIJ
    -0.07
    æŃ£åĢ¼
    -0.07
    对åŃ©åŃIJçļĦ
    -0.07
    POSITIVE LOGITS
    å½ĵä¹ĭæĹłæĦ§
    0.10
    å¥łåŁº
    0.08
    ä¹ĭä½ľ
    0.08
    å¥łå®ļ
    0.07
    èĮĥæľ¬
    0.07
     emer
    0.07
    à¸¹à¸Ľ
    0.07
    å¥łå®ļäºĨ
    0.07
    èĮĥä¾ĭ
    0.07
    纫
    0.07
    Activations Density 0.150%

    No Known Activations