© 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. 48486
    Prev
    Next
    INDEX
    Explanations

    vs/parallel comparisons

    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
    enam
    -0.08
    amax
    -0.08
    äch
    -0.08
    inke
    -0.08
    OrDefault
    -0.08
    alai
    -0.08
    ossi
    -0.07
    panse
    -0.07
    USTA
    -0.07
    mage
    -0.07
    POSITIVE LOGITS
    æŀģäºĨ
    0.07
    .drawLine
    0.06
    egel
    0.06
    ä¸Ķ
    0.06
    ãģĭãģ¤
    0.06
    并ä¸Ķ
    0.06
     lines
    0.06
    -lines
    0.06
    tan
    0.06
    éļĶå¤ľ
    0.06
    Activations Density 0.001%

    No Known Activations