© 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. 14441
    Prev
    Next
    INDEX
    Explanations

    plus or minus variations

    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
    -0.06
     âĨĴ
    -0.06
    جد
    -0.06
     mi
    -0.06
     haut
    -0.05
    1
    -0.05
    æĶ¾åѦåIJİ
    -0.05
     *
    -0.05
     (
    -0.05
    xDF
    -0.05
    POSITIVE LOGITS
    OwnProperty
    0.09
    esm
    0.09
     Teixe
    0.09
    estes
    0.08
    ÙĪسÙģ
    0.08
    ÑĤеа
    0.08
    ihe
    0.08
    antul
    0.08
     Ouver
    0.08
    serter
    0.08
    Activations Density 0.010%

    No Known Activations