© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14218
    Prev
    Next
    INDEX
    Explanations

    articles published herein

    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
    ä¼ĹæīĢåij¨çŁ¥
    -0.08
     donc
    -0.07
     thus
    -0.07
    ña
    -0.07
     sonst
    -0.07
     THEN
    -0.07
     Then
    -0.07
     anyway
    -0.07
     otherwise
    -0.07
    åĬłæĭ¿å¤§
    -0.06
    POSITIVE LOGITS
     there
    0.09
    ä¹Łæĺ¯æľĢ
    0.09
    为äºĨä¿ĿæĬ¤
    0.09
    为äºĨå®ŀçİ°
    0.08
    对äºİä¸Ģ个
    0.08
    为äºĨ满足
    0.08
    there
    0.08
    为äºĨ
    0.08
    为äºĨéģ¿åħį
    0.08
    éĹ®é¢ĺæĿ¥äºĨ
    0.08
    Activations Density 0.248%

    No Known Activations