© 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. 10167
    Prev
    Next
    INDEX
    Explanations

    Keywords or edits

    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
    åıĬåĪ©æģ¯
    -0.07
    ught
    -0.07
    irectory
    -0.07
    éĥ½å¸Ĥè¨Ģæĥħ
    -0.07
    åħ¶è¡Į为
    -0.07
    lopedia
    -0.07
    ILog
    -0.07
    ãĥ«ãĥĪ
    -0.07
    uruh
    -0.07
    ymb
    -0.07
    POSITIVE LOGITS
    unn
    0.08
    lite
    0.07
    rophic
    0.07
    еÑģÑĤве
    0.07
    atina
    0.07
    èijĹ
    0.06
    çļĦå°±æĺ¯
    0.06
     @$_
    0.06
    Forg
    0.06
     resent
    0.06
    Activations Density 0.016%

    No Known Activations