© 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. 3597
    Prev
    Next
    INDEX
    Explanations

    variable or code assignment

    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
    anka
    -0.07
    ãĤĴãĤ¹ãĥĪãĥĥãĤ¯
    -0.07
    æĶ¶èĹıæľ¬ç«Ļ
    -0.07
    icano
    -0.07
    æºľ
    -0.07
    zun
    -0.06
    owski
    -0.06
    AdapterFactory
    -0.06
    .serializer
    -0.06
    解ä½ĵ
    -0.06
    POSITIVE LOGITS
    åħ¶æ¬¡æĺ¯
    0.07
    ruc
    0.07
    rax
    0.07
    æ¸ħ纯
    0.07
    ernet
    0.06
    raig
    0.06
    ä¸Ģ身
    0.06
    olen
    0.06
    atter
    0.06
    hei
    0.06
    Activations Density 0.347%

    No Known Activations