© 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. 26785
    Prev
    Next
    INDEX
    Explanations

    academic levels and institutions

    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
    ResultSet
    -0.08
    ÙĤاب
    -0.08
    itiv
    -0.07
    imis
    -0.07
    urat
    -0.07
    åĪ«æľī
    -0.07
    à¹ģà¸Ħ
    -0.07
     Legislat
    -0.07
     hect
    -0.07
     Fabriz
    -0.07
    POSITIVE LOGITS
    级
    0.07
    -level
    0.07
     ìĪĺì¤Ģ
    0.07
     level
    0.07
    ÑĢовенÑĮ
    0.07
    èĮĥåĦ¿
    0.06
     operations
    0.06
    ENZ
    0.06
    éĶ¦æ±Ł
    0.06
    ce
    0.06
    Activations Density 0.003%

    No Known Activations