© 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. 51172
    Prev
    Next
    INDEX
    Explanations

    time units or numerical values

    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
    æĪIJç«ł
    -0.08
     Че
    -0.07
    éºŁ
    -0.07
    run
    -0.07
    åŀ£
    -0.07
    çĩĥ
    -0.07
     consum
    -0.06
    è·ij
    -0.06
     run
    -0.06
    emma
    -0.06
    POSITIVE LOGITS
    åŁºåĩĨ
    0.09
    ãĥĻãĥ¼ãĤ¹
    0.08
     baseline
    0.08
     base
    0.08
    stract
    0.08
    LogFile
    0.08
    æĹłåīį
    0.07
    _baseline
    0.07
    åŁºæķ°
    0.07
    pecting
    0.07
    Activations Density 0.033%

    No Known Activations