© 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. 20488
    Prev
    Next
    INDEX
    Explanations

    metric splits

    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
    婪
    -0.08
    requ
    -0.07
    åıĬéĻĦåĬł
    -0.07
     afer
    -0.07
    piring
    -0.07
    éĿĴ
    -0.07
    éľĢè¦ģå°Ĩ
    -0.07
    bish
    -0.07
    _spectrum
    -0.07
     pregn
    -0.06
    POSITIVE LOGITS
    éģµå¾ª
    0.08
    ä¸įä¹ħçļĦ
    0.07
    ابط
    0.07
    满足
    0.07
    è°ģ家
    0.07
     obey
    0.07
     satisfies
    0.07
    hom
    0.07
     obe
    0.07
     satisfy
    0.07
    Activations Density 0.005%

    No Known Activations