© 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. 37905
    Prev
    Next
    INDEX
    Explanations

    results or output

    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
    çĶŁçĶŁ
    -0.08
    اÙĨت
    -0.07
    ä¸Ģæĸ°
    -0.07
    åı£ä¸Ń
    -0.07
    Ober
    -0.06
     klima
    -0.06
    ectar
    -0.06
    anski
    -0.06
    ort
    -0.06
    Reducers
    -0.06
    POSITIVE LOGITS
    eps
    0.07
    人åħ³æ³¨
    0.07
    èİħ
    0.07
    尼迪
    0.07
    éģĵéķ¿
    0.07
    ToFront
    0.07
    edium
    0.07
    ccount
    0.07
    anford
    0.07
    æĹłèĥ½ä¸ºåĬĽ
    0.07
    Activations Density 0.002%

    No Known Activations