© 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. 17574
    Prev
    Next
    INDEX
    Explanations

    negation and uncertainty

    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
    erti
    -0.08
    åIJĴ
    -0.08
    çŁ¥ä¹ĭ
    -0.08
    nest
    -0.07
    éĽĨéķĩ
    -0.07
    pmat
    -0.07
    gege
    -0.07
    infeld
    -0.07
    ?,?,
    -0.07
    ihal
    -0.07
    POSITIVE LOGITS
    è½»æĺĵ
    0.09
     unless
    0.07
    åĨįæľī
    0.07
    è´¸çĦ¶
    0.07
    ä¹Łå°±ä¸į
    0.07
    æĮĩæľĽ
    0.06
    éĻ¤éĿŀ
    0.06
    寻常
    0.06
    ä¹Łä¸įè¡Į
    0.06
    roph
    0.06
    Activations Density 0.019%

    No Known Activations