© 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. 62946
    Prev
    Next
    INDEX
    Explanations

    Ideally

    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
    æīĢ以ä»ĸ
    -0.10
    éĤ£ä»ĸ
    -0.10
    èĢĮä»ĸ
    -0.09
    éĤ£æĪijå°±
    -0.09
    éĤ£æĪij
    -0.08
    æīĢ以她
    -0.08
    æīĢ以æīį
    -0.08
    æķħèĢĮ
    -0.08
    çĦ¶åIJİåıĪ
    -0.08
    éĤ£ä½ł
    -0.08
    POSITIVE LOGITS
    ï¼Į
    0.11
     there
    0.11
    Ùĭ
    0.11
    ,the
    0.10
    ØĮ
    0.09
    there
    0.09
    ently
    0.09
    mente
    0.09
    ìłģìľ¼ë¡ľ
    0.08
    ,it
    0.08
    Activations Density 0.267%

    No Known Activations