© 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. 33111
    Prev
    Next
    INDEX
    Explanations

    `here is`

    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
    abwe
    -0.09
    çļĦ设计é£İæł¼
    -0.08
    -enter
    -0.07
    -mediated
    -0.07
    abad
    -0.07
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    -0.07
    ä¸Ģç½ij
    -0.07
    ÙĬرÙĪ
    -0.07
    engo
    -0.07
    zwi
    -0.07
    POSITIVE LOGITS
    çĶŁãģ¾
    0.07
    odo
    0.07
    èĭ
    0.07
    åĮĹæĸ¹
    0.06
    reme
    0.06
    पर
    0.06
    uzu
    0.06
    ODO
    0.06
    è§Ĩ
    0.06
    çIJĨçĶ±æĺ¯
    0.06
    Activations Density 0.032%

    No Known Activations