© 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. 29125
    Prev
    Next
    INDEX
    Explanations

    abstract sections

    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
    atural
    -0.08
     offsetof
    -0.07
    姥
    -0.07
    sid
    -0.06
    abal
    -0.06
    èĤĨ
    -0.06
    éħ¢
    -0.06
    æħ·
    -0.06
    ä»İ鼶
    -0.06
    bund
    -0.06
    POSITIVE LOGITS
    çĶ¨æĪ·ä¸Ĭä¼ł
    0.08
    æĸ¯åħĭ
    0.07
    èĽ
    0.07
     :</
    0.07
    _probe
    0.07
    ãĥŃãĥ¼ãĤº
    0.07
     angef
    0.07
    mainen
    0.07
    æĽ¾èİ·
    0.07
    é¹ıé£ŀ
    0.07
    Activations Density 0.001%

    No Known Activations