© 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. 55505
    Prev
    Next
    INDEX
    Explanations

    first

    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
    cesa
    -0.08
    żu
    -0.08
    à¹ģà¸Ĺà¸Ļ
    -0.07
    æľī计åĪĴ
    -0.07
     dig
    -0.07
    essar
    -0.07
    å¢ŀåıij
    -0.06
    luv
    -0.06
    èĻ
    -0.06
    ingers
    -0.06
    POSITIVE LOGITS
    å¿ħé¡»åħĪ
    0.09
    åħĪè¡Į
    0.09
    æľĢç®Ģåįķ
    0.09
    å°±åħĪ
    0.08
    é¦ĸåħĪ
    0.08
    æĪij们åħĪ
    0.08
    æľĢåħĪ
    0.07
    é¦ĸåħĪåľ¨
    0.07
    æ¯Ķè¾ĥç®Ģåįķ
    0.07
    PTR
    0.07
    Activations Density 0.033%

    No Known Activations