© 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. 19931
    Prev
    Next
    INDEX
    Explanations

    comparison operators and comparisons

    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
     ê²ĥìĿ¸ê°Ģ
    -0.06
     absoluto
    -0.06
    ersatz
    -0.06
    ä¸ĭåİ»äºĨ
    -0.06
    ëĵĿ
    -0.06
    Æ°á»Łng
    -0.06
    BrowserRouter
    -0.06
    æ³¢å°Ķ
    -0.06
    è¡¥çŁŃæĿ¿
    -0.06
    天çĽĸ
    -0.06
    POSITIVE LOGITS
    iles
    0.05
    .
    0.05
    0.05
     Peninsula
    0.05
     unh
    0.05
    åĺī
    0.05
    cent
    0.05
    ac
    0.05
    ic
    0.05
    ull
    0.05
    Activations Density 0.019%

    No Known Activations