© 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. 30462
    Prev
    Next
    INDEX
    Explanations

    FirstReferencesAndre

    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
    abble
    -0.08
    vist
    -0.08
     Harvey
    -0.07
    ayani
    -0.07
    erule
    -0.07
    ãĥ¼ãĤ¯
    -0.07
    achel
    -0.07
    ewise
    -0.07
    roup
    -0.06
    rave
    -0.06
    POSITIVE LOGITS
    è°Ĵ
    0.07
    æĹłéĹ»
    0.07
    以ä¸ĭæĺ¯
    0.07
    å¦Ĥä¸ĭ
    0.07
    åħ·ä½ĵå¦Ĥä¸ĭ
    0.07
    åħ±åĪĨ
    0.07
    æĢ»ç»ĵå¦Ĥä¸ĭ
    0.07
    ÛĮÙĨÙĩ
    0.07
    便
    0.07
     lengkap
    0.07
    Activations Density 0.080%

    No Known Activations