© 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. 27440
    Prev
    Next
    INDEX
    Explanations

    prefix: hex

    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
    ../
    -0.08
    ymp
    -0.08
    æŃ»äºº
    -0.07
    aat
    -0.07
    ively
    -0.07
    æĶ¾çŁ¢
    -0.07
    trate
    -0.07
    mert
    -0.07
    èĩ´çļĦ
    -0.07
    uvre
    -0.07
    POSITIVE LOGITS
    uple
    0.11
    öger
    0.09
    zehn
    0.09
    athlon
    0.08
    ième
    0.08
    Ñĩина
    0.08
    voud
    0.08
    ivalent
    0.08
    alysis
    0.08
    -feira
    0.08
    Activations Density 0.041%

    No Known Activations