© 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. 61007
    Prev
    Next
    INDEX
    Explanations

    mathematical equations or code

    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
     _|
    -0.08
    æľīä»»ä½ķçĸijéĹ®
    -0.08
    ÑĩаÑĤÑĮ
    -0.07
     LoggerFactory
    -0.07
    ryn
    -0.07
    atalog
    -0.07
    indr
    -0.07
    ä¸Ģä½ĵçļĦ
    -0.07
    梱
    -0.07
    zym
    -0.07
    POSITIVE LOGITS
    arz
    0.07
    åĪ©çĶ¨å¥½
    0.07
    ç®ĢåĮĸ
    0.06
    çĶ¨å¥½
    0.06
    缸åħ³çŁ¥è¯Ĩ
    0.06
    ocol
    0.06
    å¤ĦçIJĨ设å¤ĩ
    0.06
    bauer
    0.06
    æ¯ħ
    0.06
    éĿŀ
    0.06
    Activations Density 0.004%

    No Known Activations