© 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. 20759
    Prev
    Next
    INDEX
    Explanations

    questions posed after "you"

    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
    istle
    -0.07
    ÙĦب
    -0.07
    纶
    -0.07
    åĨłåIJį
    -0.07
    ew
    -0.06
     Rockets
    -0.06
    adak
    -0.06
    çŀ
    -0.06
    ydd
    -0.06
    hatt
    -0.06
    POSITIVE LOGITS
    bjerg
    0.08
    ازÙĩ
    0.08
    markup
    0.07
    åĨįå¤ļ
    0.07
    oref
    0.07
     βα
    0.07
    idor
    0.06
    eral
    0.06
    so
    0.06
    aurus
    0.06
    Activations Density 0.001%

    No Known Activations