© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20690
    Prev
    Next
    INDEX
    Explanations

    copyright notice

    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
    Ø©
    -0.09
    à¹ĩà¸Ķลัà¸ļ
    -0.09
    ÑĤеÑĢÑı
    -0.08
    à§įত
    -0.08
    ation
    -0.08
    kod
    -0.08
    shire
    -0.07
    zkod
    -0.07
    ivity
    -0.07
    ness
    -0.07
    POSITIVE LOGITS
    а
    0.11
    ing
    0.10
    a
    0.10
    ا
    0.09
    ा
    0.09
    ìĹIJ
    0.08
    æĸ°åĬłåĿ¡
    0.08
    onacci
    0.08
    åĬłæĭ¿å¤§
    0.07
    ìļĶ
    0.06
    Activations Density 0.113%

    No Known Activations