© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9328
    Prev
    Next
    INDEX
    Explanations

    2π

    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
    zilla
    -0.10
    eksi
    -0.10
    zog
    -0.09
     kiá»ĩt
    -0.09
    pecific
    -0.09
    ektiv
    -0.09
    داء
    -0.09
    åĪ«èĩ´
    -0.09
    ä¿©
    -0.08
    ؤÙĦاء
    -0.08
    POSITIVE LOGITS
    秫
    0.06
    aits
    0.06
    ä¸ĢåľĪ
    0.06
    à¤Ĥत
    0.05
    è½®
    0.05
    äºĭ
    0.05
    éry
    0.05
    avelength
    0.05
    åĴĮä¸Ģ个
    0.05
    å±ij
    0.05
    Activations Density 0.003%

    No Known Activations