© 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. 27972
    Prev
    Next
    INDEX
    Explanations

    free energy

    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
    اÙģÛĮ
    -0.10
    ç§ģæľį
    -0.09
    onale
    -0.08
    IFORM
    -0.08
    tei
    -0.08
    æľĿ天
    -0.08
    ucat
    -0.08
    neau
    -0.08
     |âĢ¢
    -0.08
    iform
    -0.07
    POSITIVE LOGITS
    etus
    0.07
    -force
    0.07
    æĩ¿
    0.06
     Held
    0.06
    ä»ĸ强è°ĥ
    0.06
    礼åłĤ
    0.06
    åĬ¿
    0.06
    uten
    0.06
    åĬĽ
    0.06
    راÙĥ
    0.06
    Activations Density 0.001%

    No Known Activations