© 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. 21609
    Prev
    Next
    INDEX
    Explanations

    invasive, ablative, convulsive, amedullary, oral,abetic, oic, ergic

    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
    ively
    -0.07
    à¸ĺา
    -0.06
     Gob
    -0.06
    å±Ģåī¯å±Ģéķ¿
    -0.06
    åħīæ´ģ
    -0.05
    ÑĤаÑĤа
    -0.05
    ;;;;
    -0.05
     ','.
    -0.05
    ä¹ĭä¸į
    -0.05
    åįİæ³°
    -0.05
    POSITIVE LOGITS
    inov
    0.09
    awai
    0.08
    è¾¾æĸ¯
    0.08
    âĢ¦but
    0.08
    cott
    0.07
    erm
    0.07
    å¾Ļ
    0.07
    ç¦ģ
    0.07
    èĴĻå¾·
    0.07
    åģ¿
    0.07
    Activations Density 0.029%

    No Known Activations