© 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. 11180
    Prev
    Next
    INDEX
    Explanations

    noun followed by preposition

    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
     жÑĥ
    -0.08
    eppe
    -0.07
    ìŀij
    -0.07
    pee
    -0.07
     Johnston
    -0.07
     маÑĢÑĪÑĢÑĥÑĤ
    -0.06
    eder
    -0.06
    omotive
    -0.06
    epage
    -0.06
    uvi
    -0.06
    POSITIVE LOGITS
    å½¼æѤ
    0.09
    对åħ¶ä»ĸ
    0.09
    å½¼æѤçļĦ
    0.09
    ä¸İåħ¶ä»ĸ
    0.09
    (other
    0.09
    èĪĩåħ¶ä»ĸ
    0.08
    ä¸İåħ¶å®ĥ
    0.08
    ä»ĸãģ®
    0.08
    åĪ°åħ¶ä»ĸ
    0.08
    åħ³ç³»
    0.08
    Activations Density 0.710%

    No Known Activations