© 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. 38254
    Prev
    Next
    INDEX
    Explanations

    `|` or `div` followed by `>` or `]`

    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
    ron
    -0.07
    uple
    -0.07
    anc
    -0.07
    ural
    -0.07
    өг
    -0.07
    annon
    -0.07
    )[:
    -0.06
    /
    -0.06
    och
    -0.06
    را
    -0.06
    POSITIVE LOGITS
    iffies
    0.08
    kofen
    0.08
    ož
    0.08
    lát
    0.08
    æĸ°åĬłåĿ¡
    0.07
    ä¸įåı¯æĢĿè®®
    0.07
    身临åħ¶å¢ĥ
    0.07
    sium
    0.07
    èĩªæĭĶ
    0.07
    sök
    0.07
    Activations Density 0.002%

    No Known Activations