© 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. 29510
    Prev
    Next
    INDEX
    Explanations

    configuration list item

    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
    大年
    -0.07
     fi
    -0.06
     grip
    -0.06
    itty
    -0.06
    fi
    -0.06
    ëĸ¨
    -0.06
    .none
    -0.06
    è¿Ľåľº
    -0.06
    ÙĩÙĪر
    -0.06
    rin
    -0.06
    POSITIVE LOGITS
    ackers
    0.08
    jern
    0.08
    awks
    0.08
    abut
    0.07
    ловиÑĩ
    0.07
    gars
    0.07
    toupper
    0.07
    éºĴéºŁ
    0.07
     Vaults
    0.07
    usher
    0.07
    Activations Density 0.005%

    No Known Activations