© 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. 48180
    Prev
    Next
    INDEX
    Explanations

    predictive value and likelihood

    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
    åĩºåı£
    -0.07
    ohana
    -0.06
    ãĤ¹ãĤŃãĥ¼
    -0.06
     scatter
    -0.06
    æķ£
    -0.06
    åħĪéĶĭ
    -0.06
    çļĦ绣ä¸Ģ
    -0.06
    å¼ıåĴĮ
    -0.06
     Scatter
    -0.06
    åĩºåı£çļĦ
    -0.06
    POSITIVE LOGITS
    weigh
    0.08
     certainty
    0.08
     doub
    0.08
     weighing
    0.08
    çĸij
    0.08
    è°ĥæķ´åIJİ
    0.07
    åŃ
    0.07
    æݨæĸŃ
    0.07
     Brend
    0.07
    Confirmed
    0.07
    Activations Density 0.008%

    No Known Activations