© 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. 15542
    Prev
    Next
    INDEX
    Explanations

    radio emission, X-ray emission, quasars

    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
     Plant
    -0.07
    æ¤į
    -0.07
    plant
    -0.06
    åģ¥
    -0.06
    Plant
    -0.06
     practical
    -0.06
    èĥ
    -0.06
     cards
    -0.06
     plant
    -0.06
    èĢ
    -0.06
    POSITIVE LOGITS
     émission
    0.09
    æĮģç»ŃæĢ§
    0.09
     emitting
    0.09
    åħ³åģľ
    0.09
    ĵ¨
    0.09
     emission
    0.09
    æŃĩ
    0.09
    åıijå°Ħ
    0.09
     emisión
    0.08
    ä¸Ń继
    0.08
    Activations Density 0.086%

    No Known Activations