© 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. 7309
    Prev
    Next
    INDEX
    Explanations

    mathematical variables (n, k, theta, a) and ISO

    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
    æĢ§åľ°
    -0.09
    æĢ§çļĦ
    -0.07
    æĢ§çŃī
    -0.07
    åıĪä¸Ģ
    -0.06
    istically
    -0.06
    æĿ¥ä¹ĭ
    -0.06
     (?)
    -0.06
    ably
    -0.06
    achi
    -0.06
    æŀĹä¸Ń
    -0.06
    POSITIVE LOGITS
    schaften
    0.09
    -values
    0.08
    اء
    0.08
    bacher
    0.08
    வà¯ģ
    0.08
    éĩijéĴĪ
    0.07
    outers
    0.07
    imesteps
    0.07
    ITES
    0.07
    åĢ¼
    0.07
    Activations Density 0.006%

    No Known Activations