© 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. 43107
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives or suffixes

    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
    ä¹ĭä¸ĢçļĦ
    -0.10
    uage
    -0.09
    uft
    -0.08
    rezza
    -0.08
    æľªæŀľ
    -0.08
    å°¬
    -0.08
    ä¸Ĭ说
    -0.08
    âĢ¦),
    -0.08
    ilitation
    -0.08
    å·¥ä½ľçļĦåIJĮæŶ
    -0.08
    POSITIVE LOGITS
     enough
    0.11
     demais
    0.11
    ä¸Ķ
    0.09
     ÙĦÙĦغاÙĬØ©
    0.09
    ly
    0.08
    -looking
    0.08
    ographically
    0.08
    ä¸Ķåľ¨
    0.08
     Enough
    0.07
    izable
    0.07
    Activations Density 0.589%

    No Known Activations