© 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. 34499
    Prev
    Next
    INDEX
    Explanations

    API key and callbacks

    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
    -License
    -0.08
    ÃŃze
    -0.08
    å¼łçİī
    -0.08
    >>>>>>>
    -0.08
    æĭĽæłĩç½ij
    -0.07
     зака
    -0.07
    á»ĥn
    -0.07
    ãĤĴãĤ¹ãĥĪãĥĥãĤ¯
    -0.07
    anique
    -0.07
    å¿ĹåĪļ
    -0.07
    POSITIVE LOGITS
    resta
    0.07
    è°·
    0.06
    iais
    0.06
    ÙĩÙħا
    0.05
    åħ·
    0.05
    ÙĪاط
    0.05
    ä¸Ģæīĭ
    0.05
    æĸIJ
    0.05
    éļIJéļIJ
    0.05
    uct
    0.05
    Activations Density 0.086%

    No Known Activations