© 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. 8200
    Prev
    Next
    INDEX
    Explanations

    (born year)

    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
    ollar
    -0.09
    oller
    -0.08
    åĪĩå®ŀåģļåĪ°
    -0.08
     corrobor
    -0.08
    åľ¨å®ĥ
    -0.07
    elson
    -0.07
    ä¸įè¨ĢèĢĮåĸ»
    -0.07
    ÑĪенÑĮ
    -0.07
    转çŀ¬
    -0.07
    orra
    -0.07
    POSITIVE LOGITS
    èĩ³ä»Ĭ
    0.07
    etting
    0.07
    uzzy
    0.06
     precisamente
    0.06
    rese
    0.06
     Fuse
    0.06
    ests
    0.06
    IfNeeded
    0.06
    ÑĢиÑģÑĤ
    0.06
    æIJŃä¸Ĭ
    0.06
    Activations Density 0.505%

    No Known Activations