© 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. 17197
    Prev
    Next
    INDEX
    Explanations

    calm composure under pressure

    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
     inkl
    -0.06
     nature
    -0.06
     track
    -0.05
    åłµ
    -0.05
    èĹı
    -0.05
    icket
    -0.05
    รัà¸ģ
    -0.05
    åħ³
    -0.05
    æĬ¬å¤´
    -0.05
    YA
    -0.05
    POSITIVE LOGITS
    ä½Ļè£ķ
    0.07
    çIJĨæĢ§çļĦ
    0.06
    manos
    0.06
    åĨ·éĿĻ
    0.06
    åĨ·éĿľ
    0.06
    è²Į
    0.06
    çĽ¸å¯¹ç¨³å®ļ
    0.06
    个大
    0.06
    chein
    0.06
    efined
    0.06
    Activations Density 0.003%

    No Known Activations