© 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. 17559
    Prev
    Next
    INDEX
    Explanations

    initials or abbreviations

    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
    gether
    -0.07
    ä¸ĢåĪ»
    -0.07
    ue
    -0.07
     trò
    -0.07
    å¾ħç»Ń
    -0.06
    up
    -0.06
    ual
    -0.06
    æĥ³æ³ķ
    -0.06
     ÙĪاÙĦÙħر
    -0.06
    年级
    -0.06
    POSITIVE LOGITS
     consenting
    0.07
    avanaugh
    0.06
    ially
    0.06
     goodwill
    0.06
    reed
    0.06
    ãģĺãĤģãģ¦
    0.06
    ierungs
    0.05
     `$
    0.05
    å¤Ł
    0.05
    fte
    0.05
    Activations Density 0.232%

    No Known Activations