© 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. 64540
    Prev
    Next
    INDEX
    Explanations

    wingspan

    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
    Ùħاس
    -0.08
    说çļĦè¯Ŀ
    -0.08
    éķ¿éķ¿
    -0.08
    ÑĤемаÑĤи
    -0.08
    åľ¨å¿ħ
    -0.07
     Zem
    -0.07
     appunto
    -0.07
    微信æī«ä¸Ģæī«
    -0.07
    деле
    -0.07
    owell
    -0.07
    POSITIVE LOGITS
    (ts
    0.06
    (s
    0.06
    ahir
    0.06
     ():
    0.06
    ±
    0.06
     '~/
    0.06
     ÑģоглаÑģно
    0.06
    ncy
    0.06
    º
    0.06
    rama
    0.05
    Activations Density 0.015%

    No Known Activations