© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57246
    Prev
    Next
    INDEX
    Explanations

    stationary

    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
    agher
    -0.10
    ़
    -0.10
    alic
    -0.09
    ÑĮÑİ
    -0.09
    entra
    -0.09
    ing
    -0.09
    ÅĽni
    -0.09
    istan
    -0.09
    zijd
    -0.08
    endale
    -0.08
    POSITIVE LOGITS
    er
    0.08
    ä¸įåīį
    0.07
    Ñı
    0.07
    theless
    0.07
    ities
    0.07
    ormal
    0.07
    andalone
    0.06
    æħĭ
    0.06
    æĹłäºĭ
    0.06
    lated
    0.06
    Activations Density 0.007%

    No Known Activations