© 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. 16604
    Prev
    Next
    INDEX
    Explanations

    dental age, nutritional status

    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
    onde
    -0.09
    orme
    -0.08
    _RANDOM
    -0.07
     Fortun
    -0.07
     spiagg
    -0.07
    andatory
    -0.07
     denun
    -0.07
    ä»ĸçĶļèĩ³
    -0.07
    Dettagli
    -0.07
    agrant
    -0.07
    POSITIVE LOGITS
     know
    0.07
    æ³ŀ
    0.07
     veden
    0.07
    å¤ĸäºĭ
    0.07
    主ä¹ī
    0.06
    äºĨ解ä¸Ģä¸ĭåIJ§
    0.06
    èŀįèŀį
    0.06
    ibel
    0.06
    åŁºæľ¬åİŁçIJĨ
    0.06
    achi
    0.06
    Activations Density 0.001%

    No Known Activations