© 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. 21529
    Prev
    Next
    INDEX
    Explanations

    most important requirement

    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
    AccessException
    -0.08
     TEMP
    -0.08
    uego
    -0.07
    leh
    -0.07
    Modifiers
    -0.07
    æľ¬ç§ijæ¯ķä¸ļçĶŁ
    -0.07
    ä»Ģä¹Īäºĭæĥħ
    -0.07
    leb
    -0.07
    egrator
    -0.07
    edImage
    -0.07
    POSITIVE LOGITS
    ä¼ł
    0.08
    æľĢ常è§ģçļĦ
    0.08
     uniquely
    0.07
    çªģåĩº
    0.07
     alone
    0.07
    çĭ¬ç§Ģ
    0.07
    èĢĮå·²
    0.07
     emphas
    0.07
    æľĢ常è§ģ
    0.07
     Alone
    0.07
    Activations Density 0.003%

    No Known Activations