© 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. 45006
    Prev
    Next
    INDEX
    Explanations

    simple questions

    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
     instead
    -0.07
    éch
    -0.07
    çıį
    -0.07
    è¿Ļåı¯æĺ¯
    -0.07
    ź
    -0.07
    _interaction
    -0.07
    æĪij们è¿ĺ
    -0.07
    ä¹ĭç¥ŀ
    -0.07
    éĤ£åı¯
    -0.07
    instead
    -0.07
    POSITIVE LOGITS
    çģ
    0.07
     but
    0.07
    azon
    0.07
    Fetcher
    0.07
    æŁ¥æī¾
    0.07
    misc
    0.07
     nhÆ°ng
    0.07
     maar
    0.06
    ä½Ĩä¹Ł
    0.06
    ä½Ĩ
    0.06
    Activations Density 0.012%

    No Known Activations