© 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. 18622
    Prev
    Next
    INDEX
    Explanations

    octahedral

    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
    INCI
    -0.08
    åħ¶ä¸º
    -0.07
    itaires
    -0.07
    antina
    -0.07
     CÃģ
    -0.07
    ahkan
    -0.07
    asin
    -0.07
    kaz
    -0.07
    çļĦ好å¥ĩ
    -0.07
    æłijä¸Ĭ
    -0.07
    POSITIVE LOGITS
    èĮĥæĸĩç½ij
    0.07
    /oct
    0.07
    /or
    0.07
    edral
    0.07
    -addons
    0.07
    vorm
    0.07
    ä¸įå¼ĥ
    0.07
    åĮºåĮº
    0.07
    abbo
    0.07
    å´ĩæĺİ
    0.07
    Activations Density 0.002%

    No Known Activations