© 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. 40930
    Prev
    Next
    INDEX
    Explanations

    data fields

    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
     à¸Ļัà¹īà¸Ļ
    -0.08
     appunto
    -0.07
    ลà¹Īะ
    -0.07
    é¢Ĩå·¾
    -0.07
    kring
    -0.07
    ìĹŃ
    -0.07
     kÃŃ
    -0.07
    åĢĴäºĨ
    -0.07
    ÙģÙĪ
    -0.06
    ãĤĴéĩįãģŃ
    -0.06
    POSITIVE LOGITS
    etto
    0.08
    fäh
    0.07
    æī¬
    0.07
    _successful
    0.06
    æıļ
    0.06
    Ñĸга
    0.06
    utte
    0.06
    urette
    0.06
    edor
    0.06
    olly
    0.06
    Activations Density 0.011%

    No Known Activations