© 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. 16978
    Prev
    Next
    INDEX
    Explanations

    kinematics, rapidity, fragmentation

    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
    æ²ģ
    -0.07
     areas
    -0.07
    对åIJĦç§į
    -0.07
    沧海
    -0.07
     numeral
    -0.07
     civic
    -0.06
    çŁŃæľŁ
    -0.06
    æ¯ıå¹³æĸ¹ç±³
    -0.06
    åĩ½
    -0.06
     perennial
    -0.06
    POSITIVE LOGITS
    arget
    0.08
     azimuth
    0.08
    arent
    0.08
     rehe
    0.07
    imbus
    0.07
    elum
    0.07
    çļĦè´¨éĩıåĴĮ
    0.07
    壳
    0.07
    æĥ³çľĭ
    0.07
    ardown
    0.07
    Activations Density 0.001%

    No Known Activations