© 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. 15126
    Prev
    Next
    INDEX
    Explanations

    as a

    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
    为äºĨæĸ¹ä¾¿
    -0.08
    以为æĺ¯
    -0.08
    åľ¨æŃ¤åŁºç¡Ģä¸Ĭ
    -0.07
    å°±çŃīäºİ
    -0.07
    èľ»èľĵ
    -0.07
    为äºĨæĽ´å¥½åľ°
    -0.07
    æħµ
    -0.07
    为äºĨ满足
    -0.07
    âĤ¬“
    -0.07
    åĨ³å®ļçļĦ
    -0.07
    POSITIVE LOGITS
    åĩºçİ°åľ¨
    0.09
    ìį¨
    0.08
    rica
    0.08
    LING
    0.08
    ä¹ĭä¸ĢçļĦ
    0.07
    çľĭå¾ħ
    0.07
    itness
    0.07
    åŃĺåľ¨äºİ
    0.07
    ipan
    0.07
    utt
    0.07
    Activations Density 0.087%

    No Known Activations