© 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. 16878
    Prev
    Next
    INDEX
    Explanations

    Kot, Par, Com, K, Rev

    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
    ionales
    -0.06
    ominated
    -0.06
    zado
    -0.06
    ológica
    -0.06
    icana
    -0.06
    endenti
    -0.06
    ológicos
    -0.06
    ônicas
    -0.06
    scious
    -0.06
    atifs
    -0.06
    POSITIVE LOGITS
    uch
    0.09
    åı¥è¯Ŀ说
    0.09
    ach
    0.09
    cim
    0.09
    หมายà¸Ħวาม
    0.08
    wnd
    0.08
    å¿Ĺ强
    0.08
    iper
    0.08
    bole
    0.08
    ét
    0.08
    Activations Density 0.048%

    No Known Activations