© 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. 61443
    Prev
    Next
    INDEX
    Explanations

    stack overflow questions

    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
    å½ĵäºĭ
    -0.07
    eres
    -0.07
    vert
    -0.07
    ç»Ĩèħ»
    -0.07
    inces
    -0.07
    ationally
    -0.07
     Plan
    -0.07
    pere
    -0.07
    _plan
    -0.07
     alast
    -0.07
    POSITIVE LOGITS
    çŃĶæ¡Ī为
    0.08
     kérd
    0.07
    æĹłæķ°çļĦ
    0.07
    éĹ®çŃĶ
    0.07
     matrim
    0.07
     captcha
    0.07
     Ank
    0.07
    sst
    0.06
     questions
    0.06
    åıĬçŃĶæ¡Ī
    0.06
    Activations Density 0.005%

    No Known Activations