© 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. 46493
    Prev
    Next
    INDEX
    Explanations

    features, differences, benefits

    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
    è¿Ľåĩºåı£ä¸ļåĬ¡
    -0.08
    åħ«éĥ¨
    -0.07
    æľīä¸Ģç§į
    -0.07
    大åħ¨
    -0.07
    åħ¬åħ±æĸĩåĮĸ
    -0.06
    å°Ķå¤ļ
    -0.06
    اتÙĩÙħ
    -0.06
    éļ¾æ±Ĥ
    -0.06
    ãĥĨãĥ¼ãĤ·ãĥ§ãĥ³
    -0.06
    _PREF
    -0.06
    POSITIVE LOGITS
    .First
    0.09
    /features
    0.08
     features
    0.08
    ä¸Ģæĺ¯
    0.08
    hofer
    0.08
     Features
    0.08
    åĩłçĤ¹
    0.08
     characteristics
    0.08
    Features
    0.08
    产åĵģçī¹çĤ¹
    0.07
    Activations Density 0.341%

    No Known Activations