© 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. 12571
    Prev
    Next
    INDEX
    Explanations

    proper nouns and variable names

    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
    家å®Ŀ
    -0.08
    த
    -0.08
    ita
    -0.07
    ina
    -0.07
    æĪij好
    -0.06
    iselect
    -0.06
    ikle
    -0.06
    yz
    -0.06
    au
    -0.06
    ira
    -0.06
    POSITIVE LOGITS
    ås
    0.07
    akkan
    0.07
    avas
    0.07
    ÑĢома
    0.07
    åĢįçļĦ
    0.07
    azes
    0.07
    å¹³æ¹ĸ
    0.07
    abas
    0.07
    achs
    0.07
     ÑĪÑĤÑĥк
    0.07
    Activations Density 0.006%

    No Known Activations