© 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. 41716
    Prev
    Next
    INDEX
    Explanations

    make/makes

    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
    ehme
    -0.10
    ¸
    -0.09
    ست
    -0.08
    ized
    -0.08
    edir
    -0.08
    unittest
    -0.08
    æĪij家çļĦ
    -0.08
    isal
    -0.08
    onis
    -0.08
    isieren
    -0.08
    POSITIVE LOGITS
    åħ¶èĩªçĦ¶
    0.10
    é¢Ĩé¦Ĩ
    0.09
    æķĻäºİ
    0.09
    ergestellt
    0.08
    æĪijä¸įç¦ģ
    0.07
    HOLDER
    0.07
    å®ĥèĥ½å¤Ł
    0.07
    жание
    0.07
    ä¹ĭ以
    0.07
    å®ĥåħ·æľī
    0.07
    Activations Density 0.001%

    No Known Activations