© 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. 21026
    Prev
    Next
    INDEX
    Explanations

    quality, relevance, interesting content

    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
    ä½ľä¸ºä¸ŃåĽ½
    -0.06
    erek
    -0.06
    åħ¬è¯īæľºåħ³
    -0.06
     Accent
    -0.05
    éĺħ读åħ¨æĸĩ
    -0.05
    agio
    -0.05
    èµ°è¡Į
    -0.05
    chel
    -0.05
    VOKE
    -0.05
    ä»ħä½ľ
    -0.05
    POSITIVE LOGITS
    è´¨éĩıåĴĮ
    0.06
     humanity
    0.06
    è´¨éĩıæ£Ģæµĭ
    0.06
     جاÙħع
    0.05
    è´¨éĩı为
    0.05
    質éĩı
    0.05
    åĪļéľĢ
    0.05
     repetitive
    0.05
    quality
    0.05
    æĪ³
    0.05
    Activations Density 0.005%

    No Known Activations