© 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. 43276
    Prev
    Next
    INDEX
    Explanations

    patent numbers

    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
    å¦Ļ
    -0.08
    ë¹Ĺ
    -0.08
    éĢı
    -0.08
     Mine
    -0.07
    zyn
    -0.07
    Immutable
    -0.07
    æĭīå¾·
    -0.07
    udayaan
    -0.07
    egner
    -0.07
    Äįan
    -0.07
    POSITIVE LOGITS
     pair
    0.06
     poll
    0.06
    ä¸Ńåįİæ°ijæĹı
    0.06
    ä¸Ģèµ·åŃ¦ä¹ł
    0.06
    q
    0.06
    iq
    0.06
    æ®ĭ
    0.05
    ving
    0.05
    xz
    0.05
    isle
    0.05
    Activations Density 0.113%

    No Known Activations