© 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. 23862
    Prev
    Next
    INDEX
    Explanations

    Bayesian methods and inference

    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
    ashboard
    -0.07
    ArgumentException
    -0.06
    evity
    -0.06
    微信æī«ä¸Ģæī«
    -0.06
    Ñģев
    -0.06
    ä¸ĸçķĮ级
    -0.06
    anness
    -0.06
    æ¿Ģ
    -0.06
    orme
    -0.06
    èĢIJä¹ħ
    -0.06
    POSITIVE LOGITS
     Bayesian
    0.11
    bay
    0.10
     inference
    0.10
    elihood
    0.09
     probabil
    0.08
    Bay
    0.08
     probabilities
    0.08
    endra
    0.08
    zin
    0.08
    imat
    0.08
    Activations Density 0.011%

    No Known Activations