© 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. 20498
    Prev
    Next
    INDEX
    Explanations

    family and relationship terms

    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
    urias
    -0.06
    大ä½ĵ
    -0.06
    emming
    -0.06
    大èĩ´
    -0.05
    som
    -0.05
     Emilia
    -0.05
    èĢ³
    -0.05
    ä¸Ĭä¸ĭ
    -0.05
    emp
    -0.05
    åıĪæĢķ
    -0.05
    POSITIVE LOGITS
    UX
    0.07
    ikt
    0.07
    åĴĮå¹³
    0.06
     kiá»ĩn
    0.06
    гÑĢад
    0.06
    обÑĢ
    0.05
    误
    0.05
    اة
    0.05
    .reference
    0.05
     ÙĨØŃÙĨ
    0.05
    Activations Density 0.075%

    No Known Activations