© 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. 19297
    Prev
    Next
    INDEX
    Explanations

    "

    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
    aktion
    -0.06
    ÃŃso
    -0.05
    appar
    -0.05
    autop
    -0.05
    //
    -0.05
    ruÄį
    -0.05
    akup
    -0.05
    ews
    -0.05
    arpa
    -0.05
     paraph
    -0.05
    POSITIVE LOGITS
    h
    0.06
    igu
    0.06
    åıĪæĥ³
    0.06
    ä»ĸæĮĩåĩº
    0.06
    åĽ½ä¹ĭ
    0.05
    ä¼ĹæīĢåij¨çŁ¥
    0.05
    è²ł
    0.05
    geführ
    0.05
    kÄĻ
    0.05
    oli
    0.05
    Activations Density 0.041%

    No Known Activations