© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19603
    Prev
    Next
    INDEX
    Explanations

    rights to use

    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
    cmc
    -0.06
    ÑĮми
    -0.06
    èĩªå¦Ĥ
    -0.06
    (",",
    -0.05
    inov
    -0.05
    Ùģت
    -0.05
    çģ«éįĭ
    -0.05
    ÏĦÎŃÏģ
    -0.05
    å¨Ľæ¨ĤåŁİ
    -0.05
    Ñĩай
    -0.05
    POSITIVE LOGITS
    åĨįä»İ
    0.06
    æĬĺ
    0.05
     copies
    0.05
    ริ
    0.05
    éĤ£ä»½
    0.05
    Access
    0.05
     access
    0.05
     stolen
    0.05
    åįł
    0.05
    å°±ä»İ
    0.05
    Activations Density 0.038%

    No Known Activations