© 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. 17482
    Prev
    Next
    INDEX
    Explanations

    following mathematical symbols

    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
    çIJĨæīĢ
    -0.06
    cur
    -0.05
    ither
    -0.05
    æ¯ĶåĪ«äºº
    -0.05
    æ¯Ķå¦Ĥ说
    -0.05
     zas
    -0.05
    ãģĸ
    -0.05
    nameof
    -0.05
    çĽ¯
    -0.05
    ')}}
    -0.05
    POSITIVE LOGITS
    oot
    0.06
     Catalunya
    0.06
    åľ°éĽ·
    0.05
    ÏİÏģα
    0.05
    èĻ½çĦ¶
    0.05
     Wildcats
    0.05
     baza
    0.05
    felt
    0.05
    温çĥŃ
    0.05
     simila
    0.05
    Activations Density 0.001%

    No Known Activations