© 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. 32138
    Prev
    Next
    INDEX
    Explanations

    earth's orbit and rotation

    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
    lash
    -0.08
    atto
    -0.08
    htar
    -0.08
    ÅĽcie
    -0.08
    onese
    -0.08
    xem
    -0.08
    å¹´åįİ
    -0.08
    зоÑĢ
    -0.08
    èĩ´è¿ľ
    -0.08
    eel
    -0.07
    POSITIVE LOGITS
    quake
    0.10
    worm
    0.08
    -facing
    0.08
    's
    0.08
    -wide
    0.07
    liness
    0.07
    -centered
    0.06
    men
    0.06
     entière
    0.06
    ian
    0.06
    Activations Density 0.012%

    No Known Activations