© 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. 27382
    Prev
    Next
    INDEX
    Explanations

    propagation of delays, formulas

    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
    liness
    -0.09
    à¸Ħà¹īาà¸Ļ
    -0.08
    ernen
    -0.08
    appropri
    -0.08
    佬
    -0.08
    aksana
    -0.08
    utow
    -0.08
    ered
    -0.08
    edException
    -0.08
    izu
    -0.07
    POSITIVE LOGITS
    agation
    0.11
    æĢ§åľ°
    0.08
    ellant
    0.08
    ç¥ī
    0.08
    agate
    0.08
    osals
    0.08
    ়
    0.08
    vincia
    0.07
    atil
    0.07
    à¥ĩ
    0.07
    Activations Density 0.034%

    No Known Activations