© 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. 17909
    Prev
    Next
    INDEX
    Explanations

    -fabrication, non-exp, privacy, London-style

    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
    ews
    -0.06
    :str
    -0.05
    åİŁåĪĻä¸Ĭ
    -0.05
    èĢĮæŃ»
    -0.05
    åĶ¯ä¸Ģ
    -0.05
    insa
    -0.05
    大å¤ļ
    -0.05
    æ°¨åŁº
    -0.05
    主é¢ĺ
    -0.05
    اÙħت
    -0.05
    POSITIVE LOGITS
    ardu
    0.06
    comp
    0.06
    auce
    0.06
    åĬĪ
    0.06
    ئ
    0.06
     комп
    0.06
    atsby
    0.06
     comp
    0.06
    ledes
    0.05
     –,
    0.05
    Activations Density 0.011%

    No Known Activations