© 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. 30909
    Prev
    Next
    INDEX
    Explanations

    founded on, established in, keeping track, several cooperative, impact on

    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
     (...)
    -0.09
     *"
    -0.08
    类似éĹ®é¢ĺ
    -0.08
    [...]
    -0.07
     info
    -0.07
    ekl
    -0.07
     "
    -0.07
    akin
    -0.07
    inks
    -0.07
    (...)
    -0.07
    POSITIVE LOGITS
    åħ·æľī以ä¸ĭ
    0.09
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    0.08
    âĢij
    0.08
    以ä¸ĭåĩłä¸ª
    0.08
    å°ıç¼ĸ为大家
    0.08
    å©ķ
    0.07
    важа
    0.07
    以ä¸ĭåĩł
    0.07
    èĴ
    0.07
    çIJª
    0.07
    Activations Density 0.004%

    No Known Activations