© 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. 61732
    Prev
    Next
    INDEX
    Explanations

    fluid responsiveness

    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
    kreis
    -0.08
    atriz
    -0.07
    alit
    -0.07
    hren
    -0.07
    ReadStream
    -0.07
    bron
    -0.07
    丧
    -0.07
    atkan
    -0.07
    æĪ´ä¸Ĭ
    -0.07
    åIJĦåħ·
    -0.07
    POSITIVE LOGITS
     until
    0.09
    缴åĪ°
    0.08
    çºłæŃ£
    0.08
    avors
    0.08
    able
    0.08
    until
    0.08
    ible
    0.08
    åľºä¸ĬçļĦ
    0.08
     memperbaiki
    0.08
    Ùģض
    0.07
    Activations Density 0.036%

    No Known Activations