© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18241
    Prev
    Next
    INDEX
    Explanations

    ordinal adjectives and nationalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è®°èĢħäºĨ解åĪ°
    -0.06
    insen
    -0.05
    ÛĮدÙĨ
    -0.05
    inton
    -0.05
    лениÑİ
    -0.05
     evalu
    -0.05
    pulse
    -0.05
    боÑĢ
    -0.05
     بض
    -0.05
    idem
    -0.05
    POSITIVE LOGITS
    èµĦæĸĻåĴĮ
    0.07
    uely
    0.06
    fait
    0.06
    åŃĹ第
    0.06
    类游æĪı
    0.06
    æIJģ
    0.06
     useRouter
    0.06
    åıĪå¿«
    0.05
    fdf
    0.05
     antaranya
    0.05
    Activations Density 0.013%

    No Known Activations