© 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. 56875
    Prev
    Next
    INDEX
    Explanations

    before and after

    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
    éĩij丹
    -0.07
    à¸ŀล
    -0.07
    æģ¯çļĦ
    -0.07
    æģ¯
    -0.07
    ëĭ¥
    -0.07
    reis
    -0.07
    å¤ľæ·±
    -0.07
    arka
    -0.06
    apolis
    -0.06
    éŃĶæ³ķå¸Ī
    -0.06
    POSITIVE LOGITS
     nhau
    0.08
    heen
    0.07
    inhar
    0.07
    UTH
    0.06
    uve
    0.06
    ogi
    0.06
    èĩªçĦ¶èĢĮ
    0.06
    ádio
    0.06
    ฯ
    0.06
    agit
    0.06
    Activations Density 0.038%

    No Known Activations