© 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. 21089
    Prev
    Next
    INDEX
    Explanations

    instance

    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
    eve
    -0.06
    çļĦ女åĦ¿
    -0.05
    åIJİéŨ
    -0.05
    çļĦ女
    -0.05
    å®Įåħ¨ä¸į
    -0.05
    为æķ°
    -0.05
    cest
    -0.05
    veda
    -0.05
    第ä¸ĥç«ł
    -0.05
    å·²ç»ıå®Įåħ¨
    -0.05
    POSITIVE LOGITS
    çĶ³
    0.06
    åĽº
    0.06
    ä»ĸ表示
    0.06
    uges
    0.06
    afi
    0.06
    ikel
    0.05
     usually
    0.05
    éĹ®é¢ĺæŶ
    0.05
    zel
    0.05
    éĸ¢
    0.05
    Activations Density 0.013%

    No Known Activations