© 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. 56364
    Prev
    Next
    INDEX
    Explanations

    parts of codes or identifiers in URLs

    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
    óa
    -0.07
    arr
    -0.07
    eras
    -0.06
    abi
    -0.06
    èĨ©
    -0.06
    æ¯Ķäºļ
    -0.06
    odi
    -0.06
    ÑģÑĤеÑĢ
    -0.06
    SEC
    -0.06
    brightness
    -0.06
    POSITIVE LOGITS
     pitch
    0.08
    κÏį
    0.08
    _DECL
    0.07
    herits
    0.07
    acro
    0.07
    éģİçļĦ
    0.07
    ÑĨенка
    0.07
    ajem
    0.07
    itch
    0.07
     pitching
    0.07
    Activations Density 0.028%

    No Known Activations