© 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. 39367
    Prev
    Next
    INDEX
    Explanations

    geometrical shapes and parallel arrangement

    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
    æ§ĥ
    -0.08
    åĪĨäºĨ
    -0.07
    ä¸įè°ĥ
    -0.07
    åĩºåħ·
    -0.07
    稽
    -0.07
    ä¸ĭå±±
    -0.07
    æĢ»ä½ĵæĿ¥è¯´
    -0.07
    æı£
    -0.06
     waking
    -0.06
     breakup
    -0.06
    POSITIVE LOGITS
    paralle
    0.10
    çŁ©å½¢
    0.09
     paralle
    0.08
     parallel
    0.08
    å¹³è¡Į
    0.08
    并è¡Į
    0.08
    æĿ¡
    0.07
     rectangle
    0.07
    parallel
    0.07
     Parallel
    0.07
    Activations Density 0.003%

    No Known Activations