© 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. 48742
    Prev
    Next
    INDEX
    Explanations

    maximum or peak values

    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
    ernet
    -0.07
     alike
    -0.07
    æł¼å°Ķ
    -0.07
    交æį¢
    -0.07
    Ki
    -0.06
    鸿
    -0.06
     selectively
    -0.06
    าย
    -0.06
    åħŃä½į
    -0.06
    irman
    -0.06
    POSITIVE LOGITS
    æŀī
    0.08
    å¤ĦçļĦ
    0.08
    reon
    0.07
     nhá»įn
    0.07
    imum
    0.07
    çŀ©
    0.07
    Occurred
    0.07
    ĥģ
    0.07
    éĻĦè¿ij
    0.07
    åģıåIJij
    0.07
    Activations Density 0.022%

    No Known Activations