© 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. 22154
    Prev
    Next
    INDEX
    Explanations

    size reduction or smaller size

    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
    ×ķ×ķ
    -0.08
    avis
    -0.07
    tribu
    -0.07
     úl
    -0.07
    ä¸ĬæĬ¥
    -0.07
    åd
    -0.07
    à·Ĵනà·Ĭ
    -0.07
    udara
    -0.07
    íķŃ
    -0.07
    iant
    -0.07
    POSITIVE LOGITS
    æľ¬æĿ¥å°±
    0.07
    çĶ±äºİåħ¶
    0.07
    缸æ¯Ķè¾ĥ
    0.07
     tight
    0.07
    tight
    0.06
     shrinking
    0.06
     tightly
    0.06
    è¶Ĭæĺ¯
    0.06
     cram
    0.06
    owing
    0.06
    Activations Density 0.001%

    No Known Activations