© 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. 26539
    Prev
    Next
    INDEX
    Explanations

    causal connections

    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
    使ä¹ĭ
    -0.08
    使å®ĥ
    -0.07
    使åħ¶
    -0.07
    ç»®
    -0.07
    ãģĵ
    -0.07
    é½
    -0.06
    æĬĬå®ĥ
    -0.06
    ()],
    -0.06
    CRET
    -0.06
    çĶŁç´ł
    -0.06
    POSITIVE LOGITS
    å¤ĸåĬł
    0.07
    quet
    0.07
     averaging
    0.07
    éros
    0.06
    полне
    0.06
    æĮ¯åįİ
    0.06
    æĥħçIJĨ
    0.06
    è¿«ä¸įåıĬå¾ħ
    0.06
    åIJ¦åĪĻ
    0.06
    è¢ħ
    0.06
    Activations Density 0.083%

    No Known Activations