© 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. 20281
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives

    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
    пок
    -0.06
    è´´æģ¯
    -0.05
    anyag
    -0.05
    avu
    -0.05
    /de
    -0.05
     versus
    -0.05
     process
    -0.05
    zol
    -0.05
    à®Łà¯Ī
    -0.05
    æŃ³
    -0.04
    POSITIVE LOGITS
    éĥ¨åĪĨæĺ¯
    0.07
     ØŃجر
    0.06
    ç¿°
    0.06
    æľīèĩ´
    0.06
    ä¸Ģçݯ
    0.06
    件ä¸Ń
    0.06
    urally
    0.05
     part
    0.05
     acu
    0.05
    ãģ£ãģ¡
    0.05
    Activations Density 0.131%

    No Known Activations