© 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. 27186
    Prev
    Next
    INDEX
    Explanations

    let, calculate, express, did

    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
    zwi
    -0.08
    еÑĩа
    -0.07
    terna
    -0.07
     rou
    -0.07
    BackColor
    -0.07
    amour
    -0.07
    ouver
    -0.07
    reak
    -0.07
    abbo
    -0.07
    å°ı说éĺħ读
    -0.06
    POSITIVE LOGITS
    Ĥ
    0.09
    å¹²èĦĨ
    0.07
    VAR
    0.07
    ä¼ģä¸ļåIJįå½ķ
    0.07
    伸åĩºæīĭ
    0.07
    形形èī²
    0.07
    ł
    0.06
    ä¸ĢæĪIJ
    0.06
     hint
    0.06
    ï¸İ
    0.06
    Activations Density 0.005%

    No Known Activations