© 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. 46423
    Prev
    Next
    INDEX
    Explanations

    question performance

    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
    áĥĴ
    -0.07
    ium
    -0.07
    fang
    -0.06
    illon
    -0.06
    stein
    -0.06
    pon
    -0.06
    å¤ľæ·±
    -0.06
    ä¸į足ä¹ĭå¤Ħ
    -0.06
    çĤ¹åĪ°
    -0.06
    æķĪçİĩé«ĺ
    -0.06
    POSITIVE LOGITS
    /player
    0.08
    羣æŃ£åľ°
    0.08
    onat
    0.08
    [o
    0.07
    <textarea
    0.07
    &w
    0.07
    /book
    0.07
    /widget
    0.07
    =o
    0.07
     _______,
    0.07
    Activations Density 0.063%

    No Known Activations