© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29785
    Prev
    Next
    INDEX
    Explanations

    probability calculations

    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
    yu
    -0.07
    é£ŀé¾Ļ
    -0.07
    ä¸ĢåĬł
    -0.07
    áŀ»
    -0.07
    åħ¬éģĵ
    -0.07
    veen
    -0.07
    orth
    -0.06
     orth
    -0.06
    ispens
    -0.06
    iggins
    -0.06
    POSITIVE LOGITS
     probabil
    0.09
    ears
    0.08
    olos
    0.08
     probabilities
    0.08
    ikal
    0.08
    otal
    0.07
     عش
    0.07
     probability
    0.07
    cles
    0.07
    utes
    0.07
    Activations Density 0.012%

    No Known Activations