© 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. 26569
    Prev
    Next
    INDEX
    Explanations

    license

    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
    inato
    -0.08
    年代åĪĿ
    -0.08
    witz
    -0.08
    -quarters
    -0.08
    زاÙĦØ©
    -0.08
    agai
    -0.08
    éĤ¸
    -0.07
    èģĶæĴŃ
    -0.07
    Ỹ
    -0.07
    enhagen
    -0.07
    POSITIVE LOGITS
    gether
    0.16
    nd
    0.13
    ï¸ı
    0.12
    åĬłæĭ¿å¤§
    0.10
    -thirds
    0.09
    ephy
    0.09
    nde
    0.08
    ème
    0.08
    nds
    0.08
    ?family
    0.08
    Activations Density 1.293%

    No Known Activations