© 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. 60819
    Prev
    Next
    INDEX
    Explanations

    showing or proving

    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
    ä»»ä½ķä¿Ŀè¯ģ
    -0.07
    pires
    -0.07
    _ONCE
    -0.07
    说è¯ĿçļĦ
    -0.07
    å¹²ä»Ģä¹Ī
    -0.07
    adv
    -0.07
    æ¹ĸ滨
    -0.07
    çī¹éĴ¢
    -0.07
    _HEAP
    -0.06
    é«ĺå¯Ĩ
    -0.06
    POSITIVE LOGITS
    (/^\
    0.07
    足ä¸įåĩºæĪ·
    0.07
    å¾Ĺåĩº
    0.06
    ometry
    0.06
    åħ¶æŀĹ
    0.06
    åĴĮçIJĨ解
    0.06
    jum
    0.06
    çŃīå·¥ä½ľ
    0.06
    以ä¸ĭåĨħ容
    0.06
    ield
    0.06
    Activations Density 0.034%

    No Known Activations