© 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. 18807
    Prev
    Next
    INDEX
    Explanations

    plugin, interface, art, drops

    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
    ä¹İåħ¶
    -0.07
    kis
    -0.07
    ä½łåĪ°åºķ
    -0.07
     Guten
    -0.06
    åħ¬åı¸äºİ
    -0.06
    æĪij以为
    -0.06
    arsi
    -0.06
    opo
    -0.06
    æĪijè¿ĺæĺ¯
    -0.06
    æĪijåIJ¬
    -0.06
    POSITIVE LOGITS
    æ²Ļæ²Ļ
    0.07
    è¶ħéŁ³
    0.07
     Till
    0.07
    Subsystem
    0.07
    ió
    0.07
    udge
    0.07
    TER
    0.06
    ŀ
    0.06
    _PRI
    0.06
    ÙĪØ·
    0.06
    Activations Density 0.145%

    No Known Activations