© 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. 29384
    Prev
    Next
    INDEX
    Explanations

    quantities, ratings, and measurements

    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
    éĻ¤äºĨåľ¨
    -0.07
    imon
    -0.06
    åģļä»Ģä¹Ī
    -0.06
     Hur
    -0.06
    社ä¼ļåıijå±ķ
    -0.06
    ÙĪرÙĩا
    -0.06
    代表äºĨ
    -0.06
    主è¦ģæĺ¯éĢļè¿ĩ
    -0.06
    æŶæīĢ
    -0.06
    osp
    -0.06
    POSITIVE LOGITS
    å®ļ为
    0.09
    ç¡®å®ļ为
    0.08
     wynosi
    0.08
    åĪĨåĪ«ä¸º
    0.08
    ?id
    0.08
    ?=
    0.08
    æľŁä¸º
    0.07
    èĢĥäºĨ
    0.07
    _=
    0.07
     sebesar
    0.07
    Activations Density 0.103%

    No Known Activations