© 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. 49996
    Prev
    Next
    INDEX
    Explanations

    clause initiators then nouns

    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
    /of
    -0.09
    isson
    -0.09
    emble
    -0.08
    latable
    -0.07
    itol
    -0.07
    issor
    -0.07
    emm
    -0.07
    esis
    -0.07
    ר׼
    -0.07
    ibro
    -0.07
    POSITIVE LOGITS
    çĶ±æѤ
    0.09
     entanto
    0.08
     then
    0.08
     então
    0.08
    then
    0.08
    使çĶ¨è¯¥
    0.07
    åĽłæŃ¤åľ¨
    0.07
     же
    0.07
    ä¹ŁåĽłæѤ
    0.07
     latter
    0.07
    Activations Density 0.090%

    No Known Activations