© 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. 22118
    Prev
    Next
    INDEX
    Explanations

    negative or positive sentiment description

    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
    áf
    -0.05
    [..
    -0.05
     aup
    -0.05
    aling
    -0.05
    ä¸Ĭæŀ¶
    -0.05
    غا
    -0.05
    åĪ¨
    -0.05
    æ´»åĬ¨çŃī
    -0.05
    æİ¥
    -0.05
     others
    -0.05
    POSITIVE LOGITS
    æłĹ
    0.06
    ellig
    0.06
    sym
    0.06
     sindic
    0.06
    çļĦéĺħ读
    0.06
    rung
    0.06
    endar
    0.06
    omic
    0.06
     ATTRIBUTE
    0.06
    æľĢåIJİä¸Ģ次
    0.06
    Activations Density 0.038%

    No Known Activations