© 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. 48512
    Prev
    Next
    INDEX
    Explanations

    combinatorial

    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
    Ø©
    -0.09
    edImage
    -0.08
    burgh
    -0.08
    heber
    -0.07
    ward
    -0.07
    ×ķ×ķ
    -0.07
    ness
    -0.07
    ationer
    -0.07
    ation
    -0.07
    -know
    -0.07
    POSITIVE LOGITS
    raries
    0.09
    eric
    0.08
    å©ķ
    0.08
    /ge
    0.07
    ially
    0.07
    ichel
    0.07
    .ld
    0.07
    agic
    0.07
    तà¥įम
    0.07
    roid
    0.07
    Activations Density 0.003%

    No Known Activations