© 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. 17134
    Prev
    Next
    INDEX
    Explanations

    hazards and safety concerns

    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
    ç¼ĸ
    -0.06
    croft
    -0.06
    ç½ķ
    -0.06
    ä¹ĭæģ©
    -0.06
    æľīæķĪæľŁ
    -0.06
    éĶĻ
    -0.06
    .setOn
    -0.06
    çļĦå°ıåĮº
    -0.05
    è®°èĢħäºĨ解åĪ°
    -0.05
     lest
    -0.05
    POSITIVE LOGITS
     payouts
    0.05
    ibil
    0.05
    aste
    0.05
    ç´łåħ»
    0.05
    å¿«èĬĤå¥ı
    0.05
    bef
    0.05
    lena
    0.05
    è¾Ľèĭ¦äºĨ
    0.05
    erus
    0.05
    åĤį
    0.05
    Activations Density 0.003%

    No Known Activations