© 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. 55358
    Prev
    Next
    INDEX
    Explanations

    view or analysis

    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
    pong
    -0.08
    åħħåĪĨ
    -0.07
    åĴĮæıIJé«ĺ
    -0.07
    hluk
    -0.07
    å¥ĭåıij
    -0.07
    è¿Ļ个éģĵçIJĨ
    -0.06
    èĢĮå¼ķèµ·
    -0.06
    rip
    -0.06
    çIJĨæīĢå½ĵçĦ¶
    -0.06
    çīŁ
    -0.06
    POSITIVE LOGITS
    åħįè´¹çīĪ
    0.08
    è¿Ľè¡Įä¸Ń
    0.08
    bol
    0.08
    人æĪĸ
    0.08
    ä¹Łè¡Į
    0.07
    ä½ľä¸ºä¸Ģç§į
    0.07
    åľŁè±ª
    0.07
     Whole
    0.07
    hol
    0.07
    @$
    0.07
    Activations Density 0.014%

    No Known Activations