© 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. 25269
    Prev
    Next
    INDEX
    Explanations

    public

    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
    ly
    -0.09
    åĴĮ
    -0.07
    ir
    -0.07
    raries
    -0.07
    ively
    -0.07
    çİ©è¿ĩ
    -0.06
    ually
    -0.06
    añ
    -0.06
    {})
    -0.06
    ä¹İåħ¶
    -0.06
    POSITIVE LOGITS
    nable
    0.09
    jenigen
    0.08
    ulette
    0.08
    engeb
    0.07
    akhstan
    0.07
    ewed
    0.07
    ript
    0.07
    poruÄį
    0.07
    ãĥĵãĥ¼
    0.07
    åĪĨ许
    0.07
    Activations Density 0.001%

    No Known Activations