© 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. 14615
    Prev
    Next
    INDEX
    Explanations

    let's

    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
    atz
    -0.08
    sse
    -0.08
    lfw
    -0.08
    лек
    -0.08
    ément
    -0.07
    accep
    -0.07
    voli
    -0.07
    acqu
    -0.07
    ÄĻcz
    -0.07
    à¹Ģà¸ŀลิà¸ĩ
    -0.07
    POSITIVE LOGITS
    ness
    0.08
    al
    0.07
    ting
    0.07
    ième
    0.07
    ation
    0.06
    Ø©
    0.06
    lah
    0.06
    å·§
    0.06
    ä¸Ģå±Ģ
    0.06
    ãģ¦
    0.06
    Activations Density 0.009%

    No Known Activations