© 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. 33524
    Prev
    Next
    INDEX
    Explanations

    anemia and related conditions

    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
    éľĩ
    -0.07
     replay
    -0.07
     teleport
    -0.07
     Handel
    -0.07
    /plugin
    -0.06
    aurus
    -0.06
    æ¥
    -0.06
    upe
    -0.06
    尺度
    -0.06
    ublic
    -0.06
    POSITIVE LOGITS
    è¡Ģ红èĽĭçĻ½
    0.16
    æĢ§è´«è¡Ģ
    0.15
    è´«è¡Ģ
    0.15
    è¡¥è¡Ģ
    0.15
     anemia
    0.13
    红ç»Ĩèĥŀ
    0.13
    è¡Ģ红
    0.13
    ä¸Ńéĵģ
    0.13
    éĢłè¡Ģ
    0.12
    è¡ĢçļĦ
    0.12
    Activations Density 0.085%

    No Known Activations