© 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. 3044
    Prev
    Next
    INDEX
    Explanations

    Chocolate, cacao, Pope, Soap, EntityManager

    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
    er
    -0.10
    éħİ
    -0.09
    ourd
    -0.09
    ered
    -0.08
    assing
    -0.08
    ath
    -0.08
    eru
    -0.08
    colo
    -0.08
    ela
    -0.08
    rom
    -0.08
    POSITIVE LOGITS
    istic
    0.08
    ยัà¸ĩ
    0.08
    ablish
    0.07
    0.07
    бÑĥдÑĮÑĤе
    0.07
    ãĤį
    0.07
    avourites
    0.07
    ModelProperty
    0.06
    ../../../
    0.06
    Ùħ
    0.06
    Activations Density 1.009%

    No Known Activations