© 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. 38325
    Prev
    Next
    INDEX
    Explanations

    can't

    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
    er
    -0.11
    ×Ļ×Ŀ
    -0.10
    æĪĸå¤ļ个
    -0.10
    ات
    -0.09
    ãģĺãĤģãģ¦
    -0.09
    erat
    -0.09
    à¥įà¤ŀ
    -0.09
    es
    -0.09
    иÑİ
    -0.08
    áĢº
    -0.08
    POSITIVE LOGITS
    ×ķ
    0.11
    ìį¨
    0.10
    repid
    0.08
    çĦ¶å¤§
    0.08
    nie
    0.08
    تÙĬ
    0.08
    ral
    0.08
    tle
    0.07
    ter
    0.07
    ãĢħ
    0.07
    Activations Density 0.027%

    No Known Activations