© 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. 61970
    Prev
    Next
    INDEX
    Explanations

    the original

    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
    ouer
    -0.08
    ikota
    -0.08
    æľīå¿ĥ人
    -0.08
    anita
    -0.08
    asuk
    -0.08
    -tests
    -0.08
     >/
    -0.08
    ÙĦات
    -0.08
    åĪĨ许
    -0.07
    ä¸įè¡ĮäºĨ
    -0.07
    POSITIVE LOGITS
    sk
    0.06
     ↵
    0.06
    is
    0.06
    åħĢ
    0.06
    und
    0.06
    unds
    0.06
    0.06
     convert
    0.06
    ä¸ĩåĪĨ
    0.06
     veget
    0.06
    Activations Density 0.001%

    No Known Activations