© 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. 18330
    Prev
    Next
    INDEX
    Explanations

    Units and quantities like /kg and /g

    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
    å¤ļä¸ªåĽ½å®¶
    -0.06
    oen
    -0.05
    ÙĬا
    -0.05
     particular
    -0.05
    ena
    -0.05
    depend
    -0.05
    ULK
    -0.05
    æĽ´å¤ļ人
    -0.05
    af
    -0.05
    yen
    -0.05
    POSITIVE LOGITS
    ä¸ļåĬ¡åŁ¹è®Ń
    0.06
    emper
    0.06
    å½»
    0.06
    éré
    0.05
    è¾¾æłĩ
    0.05
    nama
    0.05
    мÑĸ
    0.05
    ä¸ĭåIJĮ
    0.05
    ilh
    0.05
    macher
    0.05
    Activations Density 0.005%

    No Known Activations