© 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. 46115
    Prev
    Next
    INDEX
    Explanations

    structural characteristics

    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
    gence
    -0.09
    ÃŃso
    -0.09
    brick
    -0.08
    izzi
    -0.08
    grim
    -0.08
    creens
    -0.08
    osu
    -0.08
    ÑģÑı
    -0.08
    รวมà¸ĸึà¸ĩ
    -0.08
    centage
    -0.08
    POSITIVE LOGITS
    sWith
    0.10
    Ø©
    0.09
    ists
    0.09
    i
    0.08
    iÄĩ
    0.08
    lyn
    0.07
    ت
    0.07
    ÙĬØ©
    0.07
    失è°ĥ
    0.07
    æĢ§åľ°
    0.07
    Activations Density 0.003%

    No Known Activations