© 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. 31118
    Prev
    Next
    INDEX
    Explanations

    answers and solutions

    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
    éĺħè¯»æľ¬æĸĩåīį
    -0.07
    ä¸į欲
    -0.06
    æĭŃ缮
    -0.06
     interd
    -0.06
    ToShow
    -0.06
    æĢ»ä¹¦è®°
    -0.06
    éļıæŶ
    -0.06
     dictate
    -0.06
    çŁ¥ä¹ĭ
    -0.06
     tot
    -0.06
    POSITIVE LOGITS
    mates
    0.08
    endors
    0.08
    udin
    0.08
    urette
    0.08
    iban
    0.08
    arez
    0.08
     alternativa
    0.07
    Äija
    0.07
    lando
    0.07
    å¼
    0.07
    Activations Density 0.012%

    No Known Activations