© 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. 40268
    Prev
    Next
    INDEX
    Explanations

    critical temperature transition

    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
    äºİä¸Ģ
    -0.07
    ÙĦÙĥ
    -0.07
     Angular
    -0.06
    éĤ£åı¯
    -0.06
    zek
    -0.06
    mx
    -0.06
    engine
    -0.06
     DIRE
    -0.06
     blinds
    -0.06
    åı¯è¡Į
    -0.06
    POSITIVE LOGITS
    isson
    0.08
    æµ·é»ĺ
    0.08
    ffset
    0.08
    åľ¨åį³
    0.07
    udem
    0.07
    hti
    0.07
    herits
    0.07
    hazi
    0.07
    adero
    0.07
    minor
    0.07
    Activations Density 0.005%

    No Known Activations