© 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. 57208
    Prev
    Next
    INDEX
    Explanations

    laser and amplifier

    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
    çī¡
    -0.07
    åĪ¶å®ļ
    -0.07
    ÑĤал
    -0.07
    anni
    -0.06
    ä¼łè¾¾
    -0.06
    çª
    -0.06
    山海
    -0.06
    æĹłæĿĥ
    -0.06
    æµĭå®ļ
    -0.06
    å¤ĦçIJĨæĸ¹å¼ı
    -0.06
    POSITIVE LOGITS
     spontan
    0.09
    è¾ĵåĩºåĬŁçİĩ
    0.09
     spontaneous
    0.09
    æ¿ĢåħīåĻ¨
    0.09
     pumped
    0.09
     spontaneously
    0.09
    yarat
    0.08
     espont
    0.08
    _oper
    0.08
     amplifier
    0.08
    Activations Density 0.032%

    No Known Activations