© 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. 62956
    Prev
    Next
    INDEX
    Explanations

    additive or multiplicative

    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
    ï¸ı
    -0.09
    ness
    -0.09
    Ø©
    -0.09
    éĹ´çĽĺçªģåĩº
    -0.08
    scape
    -0.08
    gether
    -0.07
    arana
    -0.07
    INGS
    -0.07
    heet
    -0.07
    abouts
    -0.07
    POSITIVE LOGITS
    æĢ§çļĦ
    0.09
    onso
    0.08
    uku
    0.08
    en
    0.08
    zij
    0.08
    licative
    0.08
    mira
    0.08
    uko
    0.08
    umo
    0.08
    bine
    0.08
    Activations Density 0.005%

    No Known Activations