© 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. 22943
    Prev
    Next
    INDEX
    Explanations

    must abide by

    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
    osso
    -0.08
    ÙĥÙī
    -0.07
    eldes
    -0.07
    ä¹ĭæĺŁ
    -0.07
    æıIJéĨĴæĤ¨
    -0.07
    ucha
    -0.07
    ervi
    -0.07
    Ïĩεί
    -0.07
    åĬªåĬĽåľ°
    -0.07
    åĬĽéĩıçļĦ
    -0.07
    POSITIVE LOGITS
    ä¸Ģå¾ĭ
    0.09
    éĻ¤
    0.08
    ä»İåħ¶
    0.07
    æ¯ĹéĤ»
    0.07
    æ¯Ķçħ§
    0.07
    绣绣
    0.07
    åĩıåįĬ
    0.07
    è§Ĩ为
    0.06
     Except
    0.06
    æĢİä¹ĪåĬŀ
    0.06
    Activations Density 0.023%

    No Known Activations