© 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. 16713
    Prev
    Next
    INDEX
    Explanations

    lib preceding library names

    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
    adays
    -0.07
    æīĢä½ľ
    -0.06
    ourcing
    -0.06
    è¿·
    -0.06
    alo
    -0.05
    aine
    -0.05
    AAD
    -0.05
    ×Ļ×ķת
    -0.05
    orrow
    -0.05
    ikov
    -0.05
    POSITIVE LOGITS
    asikan
    0.09
    зиÑĢа
    0.08
    Å¡ina
    0.08
    bies
    0.08
    cies
    0.08
    PLICIT
    0.08
    hest
    0.08
    eme
    0.08
    ê³±
    0.08
    ações
    0.08
    Activations Density 0.048%

    No Known Activations