© 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. 28807
    Prev
    Next
    INDEX
    Explanations

    second, again, permanent, day

    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
    ot
    -0.08
    otin
    -0.07
    iffer
    -0.07
    artos
    -0.07
    ern
    -0.07
    夺å¾Ĺ
    -0.06
    iston
    -0.06
    çĶ¸
    -0.06
    ankan
    -0.06
    åıĪ没æľī
    -0.06
    POSITIVE LOGITS
    缸æ¯Ķäºİ
    0.14
    缸è¾ĥäºİ
    0.14
    ä¸įåĨįæĺ¯
    0.13
    ä¸įåĥı
    0.13
    缸æ¯Ķ
    0.12
    èĢĮä¸įæĺ¯
    0.12
     beyond
    0.12
     compared
    0.12
     instead
    0.12
    ä¸įåIJĮäºİ
    0.12
    Activations Density 0.980%

    No Known Activations