© 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. 28379
    Prev
    Next
    INDEX
    Explanations

    so, implies, means

    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
    Ŀ¼
    -0.07
    å®Įåħ¨æĺ¯
    -0.07
    å°±æĪIJ为
    -0.07
    Õ¸ÖĤÕ¶
    -0.07
    åĽłä¸ºå®ĥ们
    -0.07
    ggio
    -0.07
    åı¯æĺ¯æĪij
    -0.07
    culo
    -0.07
    尿裤
    -0.07
    åı¯éĢīä¸Ń
    -0.07
    POSITIVE LOGITS
     ruth
    0.07
    é¼İé¼İ
    0.07
    égi
    0.07
    iram
    0.07
    æĪij们æľī
    0.07
    ervo
    0.07
    æĪij们ä¸įèĥ½
    0.07
    anta
    0.07
    eli
    0.07
    гада
    0.07
    Activations Density 0.008%

    No Known Activations