© 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. 25917
    Prev
    Next
    INDEX
    Explanations

    research and development

    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
    tat
    -0.07
    aler
    -0.07
     menghind
    -0.07
    æŶèĩ³
    -0.07
    pier
    -0.06
    ç¾İ好çļĦåĽŀå¿Ĩ
    -0.06
    rk
    -0.06
    edet
    -0.06
    roż
    -0.06
    åħĪå°Ĩ
    -0.06
    POSITIVE LOGITS
    ç½²
    0.08
     inv
    0.07
    ást
    0.07
    JAKARTA
    0.07
    apers
    0.07
    _INDEX
    0.07
    åŁŁ
    0.07
     barr
    0.07
    ovich
    0.06
    åħŃä½į
    0.06
    Activations Density 0.255%

    No Known Activations