© 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. 47633
    Prev
    Next
    INDEX
    Explanations

    respect

    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
    ocken
    -0.09
    ITIES
    -0.09
    é¢ĺ为
    -0.09
    ikian
    -0.09
    ities
    -0.09
    hund
    -0.09
    ligere
    -0.09
    ulario
    -0.09
    æĪĸå¤ļ个
    -0.08
    ergus
    -0.08
    POSITIVE LOGITS
    ful
    0.10
    ably
    0.10
    ingly
    0.09
    æľīåĬł
    0.08
    fully
    0.08
    lich
    0.08
    缸å¾ħ
    0.07
    AnimationFrame
    0.07
    ness
    0.07
    ueux
    0.07
    Activations Density 0.024%

    No Known Activations