© 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. 26807
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and associated events

    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
    att
    -0.08
    åı¯æĥ³
    -0.07
    enho
    -0.07
    arov
    -0.07
    åıĪä»İ
    -0.07
    atte
    -0.06
     رÙĪاÙĨ
    -0.06
     sanity
    -0.06
    evin
    -0.06
    æ´ģ
    -0.06
    POSITIVE LOGITS
    åĴĮ第
    0.14
     kalinya
    0.09
     ë²Ī째
    0.09
    次éĺħ读
    0.08
    åĴĮ第äºĮ
    0.08
    -ever
    0.08
    -generation
    0.08
    째
    0.07
    teenth
    0.07
    -most
    0.07
    Activations Density 0.243%

    No Known Activations