© 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. 20686
    Prev
    Next
    INDEX
    Explanations

    equality and comparison operators

    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
    ilon
    -0.06
    ữ
    -0.06
    urt
    -0.06
    ansir
    -0.06
    æ´ĭ
    -0.06
    oya
    -0.06
    éf
    -0.05
    rama
    -0.05
    assed
    -0.05
    scoped
    -0.05
    POSITIVE LOGITS
    æĺ¯éĽĨ
    0.06
     inse
    0.06
    ä¾ĭåŃIJ
    0.06
    idl
    0.05
     reelection
    0.05
    ä¸įæķ¢
    0.05
    ç»ĨèĬĤ
    0.05
    -detail
    0.05
    andre
    0.05
     detail
    0.05
    Activations Density 0.022%

    No Known Activations