© 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. 48711
    Prev
    Next
    INDEX
    Explanations

    Roman numerals or lists

    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
     recur
    -0.06
    榴
    -0.06
    á»ĵng
    -0.06
    eki
    -0.06
    éĺħè¯»æľ¬æĸĩåīį
    -0.06
    çĨŁ
    -0.06
    ç»Ļä¸İ
    -0.06
    天使
    -0.06
    ago
    -0.06
    pk
    -0.06
    POSITIVE LOGITS
    æ²½
    0.11
    AXB
    0.07
    å·¥ä½ľæĸ¹æ¡Ī
    0.07
    xes
    0.07
    routes
    0.07
    æīİåħĭ
    0.07
    ĥĿ
    0.07
    IID
    0.07
    rific
    0.07
    æĬĵå®ŀ
    0.07
    Activations Density 0.004%

    No Known Activations