© 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. 61813
    Prev
    Next
    INDEX
    Explanations

    gel, hydrogels, alginate, fiber

    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
    缶
    -0.08
    éĵĿæĿ¿
    -0.08
    æ²¹åĵģ
    -0.08
     brass
    -0.07
     Brass
    -0.07
    éĴ£éĩij
    -0.07
     buzzing
    -0.07
    åĩ¿
    -0.07
     Painting
    -0.07
     striking
    -0.07
    POSITIVE LOGITS
    åĩĿèĥ¶
    0.10
     gel
    0.10
     ìĪĺìļ©
    0.09
    gel
    0.09
    igel
    0.09
    åIJ¸æ°´
    0.09
    çº¤ç»´ç´ł
    0.09
    acellular
    0.09
    纤维
    0.08
     maxlength
    0.08
    Activations Density 0.118%

    No Known Activations