© 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. 58628
    Prev
    Next
    INDEX
    Explanations

    code blocks with variable assignments

    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
    hausen
    -0.08
    ç»ĵäºĨ
    -0.07
    ode
    -0.07
    apl
    -0.07
    åĩºæ¸¸
    -0.07
    Ùĩاب
    -0.07
     Cunha
    -0.07
    acula
    -0.07
    åĨ·æ°Ķ
    -0.07
    áb
    -0.06
    POSITIVE LOGITS
    ä½
    0.08
    ikes
    0.07
    æĮĩå®ļ
    0.07
    heritance
    0.07
     prescribed
    0.07
    为åħ¶
    0.07
    stub
    0.07
    ours
    0.07
    attended
    0.07
    åį±éĻ©æĢ§
    0.07
    Activations Density 0.012%

    No Known Activations