© 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. 3878
    Prev
    Next
    INDEX
    Explanations

    medical condition risks

    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
    è¾¾åħĭ
    -0.07
    ëĮĢë¡ľ
    -0.07
    ÄĻd
    -0.07
     Saigon
    -0.07
    propri
    -0.06
     undermin
    -0.06
    è®¤çľŁè´¯å½»
    -0.06
    _TRANSFER
    -0.06
    orial
    -0.06
    å¼ķèµĦ
    -0.06
    POSITIVE LOGITS
    çļĦåıijçĶŁ
    0.10
    æ¦Ĥçİĩ
    0.08
    åıijçĶŁçİĩ
    0.08
    -related
    0.08
     occurring
    0.08
     occurrence
    0.08
     outcomes
    0.08
     occurrences
    0.07
    åıijçĶŁåľ¨
    0.07
     death
    0.07
    Activations Density 0.452%

    No Known Activations