© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33220
    Prev
    Next
    INDEX
    Explanations

    end block (`}`)

    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
    çª
    -0.08
    ศี
    -0.07
    à¸ķรี
    -0.07
    Ä«g
    -0.07
    empel
    -0.06
    forsch
    -0.06
    åıijèĦ¾æ°Ķ
    -0.06
    åĪº
    -0.06
    hq
    -0.06
    erein
    -0.06
    POSITIVE LOGITS
    oger
    0.07
    inia
    0.07
    omm
    0.07
    दà¥Ģ
    0.07
    ä¸Ģå¤ķ
    0.07
     pretty
    0.07
    æĽ´æĸ°æĹ¥æľŁ
    0.07
    ubin
    0.07
    icode
    0.07
    åħ¨éĥ¨è¯Ħ论
    0.07
    Activations Density 0.041%

    No Known Activations