© 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. 22229
    Prev
    Next
    INDEX
    Explanations

    section 7 (7. Additional Terms.)

    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
    ../
    -0.12
    ../../../
    -0.11
    ../../
    -0.10
    à¹īว
    -0.09
    raries
    -0.08
    iseaux
    -0.08
    à¹ī
    -0.08
    Ùģا
    -0.08
    {//
    -0.07
    antang
    -0.07
    POSITIVE LOGITS
    ï¸ı
    0.09
    uxtap
    0.09
    edback
    0.09
    деÑģÑıÑĤ
    0.08
    eenth
    0.08
    esimo
    0.08
    ugo
    0.08
    untime
    0.08
    วà¸Ķ
    0.08
    ificant
    0.07
    Activations Density 0.488%

    No Known Activations