© 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. 61839
    Prev
    Next
    INDEX
    Explanations

    HTML, corps, efficacy, dental, mixing

    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
    æĪĸä¸İ
    -0.07
    éİ
    -0.07
    åıĬ缸åħ³
    -0.07
    KET
    -0.07
    åķ¡
    -0.07
    çģ
    -0.06
    avor
    -0.06
    串串
    -0.06
    绾ç»İ
    -0.06
    纾
    -0.06
    POSITIVE LOGITS
    vs
    0.09
    /IP
    0.09
    ensch
    0.08
    /D
    0.08
    åĴĮ
    0.08
    åĴĮé£İéĻ©
    0.08
    -vers
    0.07
    åĪļä¸Ģ
    0.07
    uld
    0.07
     maupun
    0.07
    Activations Density 0.066%

    No Known Activations