© 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. 40653
    Prev
    Next
    INDEX
    Explanations

    orsche will

    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
     dụ
    -0.07
    AtA
    -0.07
    _^
    -0.07
    å¾ģæ±ĤæĦıè§ģ稿
    -0.06
    loo
    -0.06
    ç§Ģæīį
    -0.06
     contamin
    -0.06
    åīįæıIJæĺ¯
    -0.06
     Dana
    -0.06
    çļĦèĥľåĪ©
    -0.06
    POSITIVE LOGITS
    adiens
    0.07
    _hyper
    0.07
    _lane
    0.07
    -sum
    0.07
    ennie
    0.07
     ekstrak
    0.07
    ziu
    0.07
     uta
    0.07
     differentiated
    0.06
     gaussian
    0.06
    Activations Density 0.001%

    No Known Activations