© 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. 21322
    Prev
    Next
    INDEX
    Explanations

    curves and waveforms

    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
    =$((
    -0.07
    ongo
    -0.07
    ongs
    -0.07
    Kab
    -0.07
    ä¸Ģ空
    -0.07
    ELY
    -0.07
    è¶Ĭå¤ļ
    -0.06
    osos
    -0.06
    ypass
    -0.06
    arena
    -0.06
    POSITIVE LOGITS
     curves
    0.11
    æĽ²çº¿
    0.11
     curve
    0.11
    æĽ²çº¿çļĦ
    0.11
     shape
    0.10
    /profile
    0.09
    å½¢çĬ¶
    0.09
    shape
    0.09
    -shaped
    0.09
     Shape
    0.09
    Activations Density 0.096%

    No Known Activations