© 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. 65272
    Prev
    Next
    INDEX
    Explanations

    finite and bounded

    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
    ãģ¾ãģ¾
    -0.09
    ä¸ĢåŃĹ
    -0.08
    ogle
    -0.08
    ivec
    -0.08
    æŁĶ
    -0.07
    ä¸Ģèĩ´æĢ§
    -0.07
    ä¸į对称
    -0.07
     Configur
    -0.07
    éŁ
    -0.07
    akest
    -0.07
    POSITIVE LOGITS
     finite
    0.19
    finite
    0.17
    æĺ¯æľīéĻIJçļĦ
    0.15
     Finite
    0.15
    Finite
    0.15
     finito
    0.14
    æľīéĻIJ
    0.14
    æľīéĻIJçļĦ
    0.13
     bounded
    0.13
     fin
    0.12
    Activations Density 0.027%

    No Known Activations