© 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. 25955
    Prev
    Next
    INDEX
    Explanations

    related to publishing or types

    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
    жай
    -0.08
    _instructions
    -0.07
    è¦ģæĪij
    -0.07
    truc
    -0.07
    åħ¶ä¸ŃæľĢ
    -0.07
    angi
    -0.07
    çĪº
    -0.07
    èļĤ
    -0.07
    kis
    -0.07
    άλιÏĥÏĦα
    -0.07
    POSITIVE LOGITS
    æŀī
    0.08
     Ser
    0.07
    arya
    0.07
    æĿ¥è¶Ĭ
    0.07
    eih
    0.06
    Ser
    0.06
    ç¡®å®ŀ
    0.06
    Yes
    0.06
    æĺ¯çļĦ
    0.06
    æŀľçĦ¶
    0.06
    Activations Density 0.004%

    No Known Activations