© 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. 42212
    Prev
    Next
    INDEX
    Explanations

    distinguish between or among

    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
    urts
    -0.08
    ä¼¼éĶ¦
    -0.08
    iskon
    -0.08
    izin
    -0.08
    IVITY
    -0.07
    editary
    -0.07
    ilities
    -0.07
    insen
    -0.07
    å°½æĥħçļĦ
    -0.07
    mits
    -0.07
    POSITIVE LOGITS
    ably
    0.12
    对å¾ħ
    0.10
    ately
    0.10
    å¼ĢæĿ¥
    0.09
    ERENCE
    0.09
     nhau
    0.08
    ì§ĵ
    0.08
    ãĥ³ãĤ°
    0.08
    çľŁä¼ª
    0.08
    å°įå¾ħ
    0.08
    Activations Density 0.033%

    No Known Activations