© 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. 32399
    Prev
    Next
    INDEX
    Explanations

    Caps, Festivals, Metformin, Argentine, Penetrating

    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
    IZED
    -0.08
    atifs
    -0.08
    UFFIX
    -0.07
    ÏĥÏĦα
    -0.07
    ALLY
    -0.07
    ãģŁ
    -0.07
    ativamente
    -0.07
    posa
    -0.07
    áģ
    -0.07
    ativas
    -0.06
    POSITIVE LOGITS
    ฯ
    0.09
    uit
    0.08
    istor
    0.08
    à¸Ļิ
    0.08
    enger
    0.08
    iver
    0.08
    isphere
    0.07
    ung
    0.07
    our
    0.07
    quer
    0.07
    Activations Density 0.388%

    No Known Activations