© 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. 45155
    Prev
    Next
    INDEX
    Explanations

    code and script elements

    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
    çļĦçī©çIJĨ
    -0.07
     (
    -0.07
     physical
    -0.07
    å±ħé«ĺä¸įä¸ĭ
    -0.07
    physical
    -0.06
    çħŀ
    -0.06
    ä¸įåıĬæŶ
    -0.06
    _
    -0.06
     Phys
    -0.06
    ctrine
    -0.06
    POSITIVE LOGITS
    éĢīçĶ¨
    0.10
    éģ¸çĶ¨
    0.09
    imports
    0.09
    ALLOC
    0.09
    代çłģå¦Ĥä¸ĭ
    0.09
     Auton
    0.09
     imports
    0.08
    мп
    0.08
    _VARS
    0.08
    YEAR
    0.08
    Activations Density 0.004%

    No Known Activations