© 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. 29325
    Prev
    Next
    INDEX
    Explanations

    Android Go, Windows Mobile, silicon carbide

    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
    ×ĵ×ķת
    -0.08
    esty
    -0.07
    å·įå·į
    -0.07
    à¸Łà¸²
    -0.07
    ÑĪÑĤей
    -0.07
    ÙĬسÙĬ
    -0.07
    iani
    -0.07
    shaw
    -0.07
    ="//
    -0.07
    aniel
    -0.07
    POSITIVE LOGITS
    çļĦçī¹æ®Ĭ
    0.09
     unconventional
    0.08
     неÑģÑĤандаÑĢÑĤ
    0.07
    åı¦ç±»
    0.07
    çī¹æ®ĬçļĦ
    0.07
    çŃīçī¹æ®Ĭ
    0.07
    çļĦçĭ¬çī¹
    0.06
     plus
    0.06
    ãģĭãģı
    0.06
     non
    0.06
    Activations Density 0.810%

    No Known Activations