© 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. 33778
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis)

    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
    以åıĬå¦Ĥä½ķ
    -0.08
    æĥħåĨµåıĬ
    -0.08
    ementer
    -0.07
     samt
    -0.07
    è¿ĺæĺ¯ä¸į
    -0.07
    è¿ĺ以为
    -0.07
    为éļ¾
    -0.07
    åĨħ容åıĬ
    -0.07
    ä¼ļè®®çĶ±
    -0.07
    pora
    -0.07
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.08
    lov
    0.07
    _sources
    0.07
    ä¸İä¹ĭ
    0.07
    è¿Ļæł·ä¸Ģ个
    0.07
    æľīåı²
    0.07
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.07
    !--
    0.07
    羡
    0.06
    )test
    0.06
    Activations Density 0.141%

    No Known Activations