© 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. 22883
    Prev
    Next
    INDEX
    Explanations

    json/code structure keywords

    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
    åŁĤ
    -0.07
    mar
    -0.07
    æī¬æī¬
    -0.07
    umn
    -0.07
    ajara
    -0.07
    éĺ¶
    -0.07
    estens
    -0.06
     verge
    -0.06
    å¹´ä¸ĢåŃ£åº¦
    -0.06
    backs
    -0.06
    POSITIVE LOGITS
     appunto
    0.08
    ipt
    0.07
     puss
    0.07
    ä¿¡åĩ½
    0.07
    ildi
    0.07
    èľľ
    0.07
     wel
    0.07
     wrap
    0.07
    ugo
    0.07
    éĽ¯
    0.06
    Activations Density 0.001%

    No Known Activations