© 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. 20651
    Prev
    Next
    INDEX
    Explanations

    transistor, unit, TextView, substrate

    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¿Ļä¸Ģ次çļĦ
    -0.08
     Pron
    -0.06
    gota
    -0.06
    æĺ¯ä¸įå¤Ł
    -0.06
    ãĤ¹ãĥĿ
    -0.06
    ammel
    -0.06
    çĻ¼è¨Ģ
    -0.06
    kez
    -0.06
    -threat
    -0.06
     vóc
    -0.06
    POSITIVE LOGITS
    em
    0.06
    ë¥ĺ
    0.05
    ems
    0.05
    åĽŀé¦ĸ
    0.05
    empo
    0.05
     mit
    0.05
    ç»ĦåIJĪ
    0.05
    é»Ħç´ł
    0.05
     gib
    0.05
    tmp
    0.05
    Activations Density 0.009%

    No Known Activations