© 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. 64544
    Prev
    Next
    INDEX
    Explanations

    gain, improved, best, famous

    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
    fulness
    -0.07
    çī¢çī¢
    -0.07
    pedia
    -0.07
    çļĦçĭ¬çī¹
    -0.07
    opedia
    -0.07
    åĪ¶å®ľ
    -0.07
    ç®Ģä»ĭ
    -0.06
    åľ¨åĨľæĿij
    -0.06
    etics
    -0.06
    ä¼Łä¸ļ
    -0.06
    POSITIVE LOGITS
    æĪĸå¤ļ个
    0.09
     albeit
    0.09
    ly
    0.09
    ëĤĺë§Ī
    0.08
    -looking
    0.08
    மான
    0.08
    appable
    0.08
    issime
    0.08
    æĪĸéĥ¨åĪĨ
    0.08
    ìłģìĿ¸
    0.08
    Activations Density 0.001%

    No Known Activations