© 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. 62738
    Prev
    Next
    INDEX
    Explanations

    i sin x

    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
    éĢłåĮĸ
    -0.06
    æĿ¥è¯´
    -0.06
    im
    -0.06
    带åĽŀ家
    -0.06
    åı¯äº²
    -0.05
    èĢĮä¸Ķ
    -0.05
     infatti
    -0.05
    åı¯è§ģ
    -0.05
    iterator
    -0.05
    ipe
    -0.05
    POSITIVE LOGITS
    <tool_response>
    0.09
    ä»İè½»
    0.08
    ÉĻrÉĻ
    0.08
    adian
    0.07
    otis
    0.07
    ÑģнÑĥÑİ
    0.07
    uality
    0.07
    adians
    0.07
    enter
    0.07
    áĥļáĥĶ
    0.07
    Activations Density 0.007%

    No Known Activations