© 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. 39310
    Prev
    Next
    INDEX
    Explanations

    JS/SD/csv extensions

    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
     fortun
    -0.07
    dok
    -0.07
    åĬŁèĩ£
    -0.07
    خر
    -0.07
     arro
    -0.07
    kken
    -0.07
    ubo
    -0.07
    èį·
    -0.06
    eht
    -0.06
    Feat
    -0.06
    POSITIVE LOGITS
     upside
    0.07
    èĭ¥å¹²
    0.07
    å°±åĪ«
    0.07
    æīįèĥ½å®ŀçİ°
    0.07
    IDI
    0.07
    åĪĿä¸Ģ
    0.07
    ãģ¨ãĤĤãģ«
    0.07
    羣æŃ£æĪIJ为
    0.07
    ISA
    0.06
     appunto
    0.06
    Activations Density 0.184%

    No Known Activations