© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14775
    Prev
    Next
    INDEX
    Explanations

    track/stand/wade/stake/ies/asley + in/invest/for/fin/comprises

    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
    ÑĢик
    -0.08
    ungg
    -0.08
     respective
    -0.08
     either
    -0.07
    è¾ĥ为
    -0.07
    -0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.07
    缸åºĶ
    -0.07
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.07
    rote
    -0.07
    POSITIVE LOGITS
     versus
    0.08
     vs
    0.08
    tiny
    0.07
     إذÙĨ
    0.07
    -vs
    0.07
    ány
    0.07
    æīįç®Ĺ
    0.07
    为ä»Ģä¹Īä¼ļ
    0.07
    åĨį说
    0.07
    ÒĽÑĭ
    0.07
    Activations Density 0.001%

    No Known Activations