© 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. 33430
    Prev
    Next
    INDEX
    Explanations

    asymptotes or infinities

    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
    _override
    -0.08
     bordel
    -0.07
    ainter
    -0.07
    çªį
    -0.07
    getWindow
    -0.07
    iete
    -0.07
     weighing
    -0.07
    åĥ»
    -0.07
    滥
    -0.07
    gem
    -0.06
    POSITIVE LOGITS
    æĹłéĻIJ
    0.11
     asympt
    0.10
     infinitely
    0.10
     never
    0.09
    æĹłéĻIJçļĦ
    0.09
    never
    0.09
     unreachable
    0.08
     infinite
    0.08
    çĦ¡éĻIJ
    0.08
    æ¸IJ
    0.08
    Activations Density 0.004%

    No Known Activations