© 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. 64959
    Prev
    Next
    INDEX
    Explanations

    Enter a prompt

    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
    _external
    -0.07
    ä¸Ģå®ļçļĦ
    -0.07
    ffit
    -0.07
    ÃŃk
    -0.07
    arra
    -0.07
    Wire
    -0.07
    å¾Ĺ以
    -0.07
    “They
    -0.06
    ouch
    -0.06
     опÑĢеделеннÑĭÑħ
    -0.06
    POSITIVE LOGITS
     preferably
    0.10
    ukkan
    0.09
    ведиÑĤе
    0.09
    Enter
    0.09
     Enter
    0.08
    åĽŀ车
    0.08
    请è¾ĵåħ¥
    0.08
    enter
    0.08
     enter
    0.08
    entai
    0.08
    Activations Density 0.077%

    No Known Activations