© 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. 17292
    Prev
    Next
    INDEX
    Explanations

    curved or shaped structures

    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
     blink
    -0.07
    éĺĪ
    -0.07
     Consolid
    -0.07
    PosX
    -0.07
    æĹģè§Ĥ
    -0.07
    æĹłèī²
    -0.07
    åı¯éĿł
    -0.07
    éĹ
    -0.07
    blink
    -0.06
    æĭ¼åĽ¾
    -0.06
    POSITIVE LOGITS
    æĽ²çº¿
    0.15
     curves
    0.14
     curve
    0.13
    æĽ²çº¿çļĦ
    0.13
     shape
    0.12
     shaped
    0.12
    弧度
    0.12
    æĽ²éĿ¢
    0.12
     curved
    0.12
    -shaped
    0.12
    Activations Density 0.114%

    No Known Activations