© 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. 18153
    Prev
    Next
    INDEX
    Explanations

    acupuncture and energy systems

    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®°
    -0.06
    kest
    -0.06
     spoiler
    -0.06
    eke
    -0.06
    olah
    -0.06
    øj
    -0.06
    认
    -0.06
    ÑĨеÑĢ
    -0.06
    æĪIJåħ¨
    -0.06
    æĭ¼
    -0.06
    POSITIVE LOGITS
     ISO
    0.05
    æĺ¯ä¸ĢéŨ
    0.05
     abound
    0.05
    hte
    0.05
    ESCO
    0.05
     flow
    0.05
    ä¸įçķħ
    0.05
    积èģļ
    0.05
     Windows
    0.05
    FLOW
    0.05
    Activations Density 0.013%

    No Known Activations