© 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. 2757
    Prev
    Next
    INDEX
    Explanations

    new, separate, own, individual, another, two, second

    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
    åIJ¸é£Ł
    -0.07
    tal
    -0.07
    ÑĢик
    -0.07
    inta
    -0.06
    åijĨåijĨ
    -0.06
    tas
    -0.06
    ardin
    -0.06
    aval
    -0.06
    amin
    -0.06
    wana
    -0.06
    POSITIVE LOGITS
    æĦıä¹īä¸ĬçļĦ
    0.09
    å±Ĥ次çļĦ
    0.08
    主è¦ģçļĦ
    0.08
    æľīåĬ©
    0.07
    ahaya
    0.07
    vecs
    0.07
    ÑģÑĤоÑĩ
    0.07
     Bursa
    0.07
    å¾Ĵ
    0.07
    isel
    0.07
    Activations Density 0.200%

    No Known Activations