© 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. 64414
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming contexts

    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
    à¸Ĺà¹īาà¸Ĺาย
    -0.06
    åħ±åĴĮåĽ½
    -0.06
    éļ¾æ±Ĥ
    -0.06
    éĺľ
    -0.06
    说ä¸į
    -0.06
    ague
    -0.06
    åĨ
    -0.06
    bel
    -0.05
    ined
    -0.05
     oc
    -0.05
    POSITIVE LOGITS
    å³»
    0.09
    å¾Īç®Ģåįķ
    0.08
    jaz
    0.08
    æĹłçĸijæĺ¯
    0.08
     пÑĢоÑģÑĤа
    0.08
    çĦ¡çĸij
    0.08
    sze
    0.08
    以å¤ĸ
    0.08
    æĺ¾çĦ¶
    0.07
    å½ĵçĦ¶æĺ¯
    0.07
    Activations Density 0.323%

    No Known Activations