© 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. 64696
    Prev
    Next
    INDEX
    Explanations

    respiratory system 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
    ì°į
    -0.08
    ovin
    -0.08
    ishly
    -0.08
    präg
    -0.08
    sworth
    -0.08
    æĪĸå¤ļ个
    -0.08
    imizer
    -0.07
    arity
    -0.07
    å¤ļ人
    -0.07
    itude
    -0.07
    POSITIVE LOGITS
    ational
    0.08
    ductive
    0.08
    ensible
    0.07
    an
    0.07
    orthand
    0.07
    اÙĨØ©
    0.07
    ozen
    0.06
    atoire
    0.06
    ä¸įçķħ
    0.06
    ulpt
    0.06
    Activations Density 0.028%

    No Known Activations