© 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. 24331
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
    ãĥĥãĥī
    -0.08
    éľ²æ°´
    -0.07
    /&
    -0.07
     freig
    -0.07
    @[
    -0.07
    ãģĹãģĭãģªãģĦ
    -0.07
    [__
    -0.07
    })();
    -0.07
    Ñħод
    -0.07
    polator
    -0.07
    POSITIVE LOGITS
    ä»Ĺ
    0.07
    çļĦæĿ¡ä»¶ä¸ĭ
    0.07
    ffet
    0.06
     Otherwise
    0.06
     past
    0.06
    ãģĭãģ¤
    0.06
    åIJĪåIJĮæŶ
    0.06
    次第
    0.06
    æĹıçļĦ
    0.06
    æŶ
    0.06
    Activations Density 0.011%

    No Known Activations