© 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. 2296
    Prev
    Next
    INDEX
    Explanations

    `.ed`

    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
    elden
    -0.08
    rott
    -0.08
    ard
    -0.07
     ought
    -0.07
    erve
    -0.07
     Rao
    -0.07
     Raqqa
    -0.07
    ä»°
    -0.06
    ren
    -0.06
    迸
    -0.06
    POSITIVE LOGITS
     versch
    0.07
    íĻĺ
    0.07
    fixtures
    0.06
    .Done
    0.06
     classic
    0.06
    ëĭ¤ë¦¬
    0.06
    ç»®
    0.06
    çļĦåĪ¶ä½ľæĸ¹æ³ķ
    0.06
    iw
    0.06
    æłĩåĩĨä¿¡æģ¯
    0.06
    Activations Density 0.011%

    No Known Activations