© 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. 18821
    Prev
    Next
    INDEX
    Explanations

    jelly, obtained, compost, milk

    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
    onus
    -0.09
    oczy
    -0.08
    å®°
    -0.07
    tera
    -0.07
    庸
    -0.06
     наÑı
    -0.06
    å¼ķåħ¥äºĨ
    -0.06
    对äºİä¸Ģ个
    -0.06
    æľīæĿ¡ä¸įç´Ĭ
    -0.06
     пÑĭ
    -0.06
    POSITIVE LOGITS
    åĪ¶æĪIJçļĦ
    0.10
     derived
    0.10
    çļĦåĪ¶ä½ľ
    0.10
     obtained
    0.10
     daraus
    0.09
    çļĦåĪ¶ä½ľæĸ¹æ³ķ
    0.09
     obtenido
    0.09
    çŃī产åĵģ
    0.09
     formed
    0.09
    åĪ¶ä½ľæĸ¹æ³ķ
    0.09
    Activations Density 0.291%

    No Known Activations