© 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. 61578
    Prev
    Next
    INDEX
    Explanations

    action of

    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
    iht
    -0.09
    izen
    -0.09
    iard
    -0.09
    edException
    -0.09
    å·´å¡ŀ
    -0.09
    ROY
    -0.09
    estig
    -0.09
    благо
    -0.09
    ilter
    -0.09
    urance
    -0.09
    POSITIVE LOGITS
    fully
    0.10
    ful
    0.08
    åĬĽçļĦ
    0.08
    sm
    0.07
    FUL
    0.07
    sworth
    0.07
    0.07
    lı
    0.07
    åĸļ
    0.06
    äºİå¿ĥ
    0.06
    Activations Density 0.004%

    No Known Activations