© 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. 64938
    Prev
    Next
    INDEX
    Explanations

    retrieve or fetch

    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
    eenth
    -0.09
    æ¯ħ
    -0.09
    ìį¨
    -0.08
    wurf
    -0.08
    èģĮå®Ī
    -0.08
    zinho
    -0.08
    unky
    -0.08
    åĸľéĹ»
    -0.08
    teria
    -0.08
    matic
    -0.08
    POSITIVE LOGITS
    OrCreate
    0.10
    TURE
    0.10
    ters
    0.09
    åĪ°çļĦ
    0.08
    ãģ¹ãģį
    0.08
    eer
    0.08
    ables
    0.08
    ptions
    0.08
    ãĤĪãģĨãģª
    0.08
    ণ
    0.08
    Activations Density 0.001%

    No Known Activations