© 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. 2183
    Prev
    Next
    INDEX
    Explanations

    energy units (kcal, J, mol)

    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
    naan
    -0.11
    DMETHOD
    -0.09
    ära
    -0.09
    olim
    -0.09
    ÑĦелÑĮ
    -0.09
    éĺ¿å§Ĩ
    -0.09
    ä¸Ģåı·
    -0.08
    uolo
    -0.08
    该åIJį
    -0.08
    uze
    -0.08
    POSITIVE LOGITS
     comparable
    0.08
    åij½
    0.07
    æµ·
    0.07
     C
    0.06
     comparative
    0.06
    ä½į
    0.06
     measured
    0.06
     indicative
    0.06
     Lewis
    0.06
    åĵģ
    0.06
    Activations Density 0.005%

    No Known Activations