© 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. 64769
    Prev
    Next
    INDEX
    Explanations

    science, inventions, food, products, organisms

    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
    cestor
    -0.08
     [=
    -0.08
    голо
    -0.08
    å±ħåīį
    -0.07
    corpor
    -0.07
    efore
    -0.07
    ÙĪÙĬس
    -0.07
    Ĥ¹
    -0.07
    ä¸ĬåĬł
    -0.07
    å¤ĩ好
    -0.07
    POSITIVE LOGITS
    ardy
    0.07
    oke
    0.07
    nad
    0.07
    请å°Ĩ
    0.07
    çŃ
    0.06
    inos
    0.06
    é©
    0.06
     GR
    0.06
    çĴ¨
    0.06
    iser
    0.06
    Activations Density 0.007%

    No Known Activations