© 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. 23825
    Prev
    Next
    INDEX
    Explanations

    states ofBusy, current, full, responsive

    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
    /../
    -0.08
    оÑħ
    -0.08
    俱åħ¨
    -0.08
    ippet
    -0.08
    @js
    -0.08
    _DECLARE
    -0.08
    ç¨İæĶ¶è¿Ŀæ³ķ
    -0.08
    Ł
    -0.08
    ä¿Ŀè¯ģåħ¶
    -0.07
    IsValid
    -0.07
    POSITIVE LOGITS
    ness
    0.13
    NESS
    0.09
     بÙĪدÙĨ
    0.08
    ãĥįãĤ¹
    0.08
    ward
    0.07
    ment
    0.07
     شدÙĨ
    0.06
    olan
    0.06
    度é«ĺ
    0.06
    '
    0.06
    Activations Density 0.043%

    No Known Activations