© 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. 19106
    Prev
    Next
    INDEX
    Explanations

    video production and broadcasting terms

    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
    å¿į
    -0.06
    èµı
    -0.06
    ÈĽÄĥ
    -0.06
    æIJº
    -0.06
    mediate
    -0.06
    -gallery
    -0.05
    å·¡
    -0.05
    åĹľ
    -0.05
    éľĩæĴ¼
    -0.05
    æĶ¶èĹı
    -0.05
    POSITIVE LOGITS
    äºķ
    0.06
    çķ¥æĺ¾
    0.06
    á»įng
    0.06
    é¾ĻéŨ
    0.05
    atel
    0.05
    活水
    0.05
    è´¨
    0.05
    çĹħæŃ»
    0.05
    è®¤çľŁçļĦ
    0.05
    QUAL
    0.05
    Activations Density 0.018%

    No Known Activations