© 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. 51359
    Prev
    Next
    INDEX
    Explanations

    This followed by title

    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
    ÑīÑĥ
    -0.08
     anal
    -0.08
     Politico
    -0.07
    èĢĥäºĨ
    -0.07
    æī¿æĭħä¸ĢåĪĩ
    -0.07
    anei
    -0.07
    á»±u
    -0.07
    zioni
    -0.07
    imo
    -0.07
    lico
    -0.07
    POSITIVE LOGITS
     scientists
    0.09
    ç§ijåŃ¦å®¶
    0.09
    ç§ijåѦ
    0.08
    çļĦç§ijåѦ
    0.08
     scientist
    0.08
     science
    0.08
     Science
    0.08
     scientific
    0.08
    ç§ijåŃ¦å®¶ä»¬
    0.07
    Scientists
    0.07
    Activations Density 0.383%

    No Known Activations