© 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. 17211
    Prev
    Next
    INDEX
    Explanations

    apply to, operates differently, shares records, override settings

    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
    å¾®é£İ
    -0.06
    è§ĦèĮĥè¦ģæ±Ĥ
    -0.06
    大åįĬ
    -0.06
    ergestellt
    -0.05
    è¯ķè¡Į
    -0.05
    ä¿Ŀè¯ģ责任
    -0.05
    宫å¤ĸ
    -0.05
    loh
    -0.05
    iese
    -0.05
    ä¿Ŀ証
    -0.05
    POSITIVE LOGITS
    åĴĮä¿ĿæĬ¤
    0.06
    —including
    0.06
    תר
    0.05
    åĮħæĭ¬
    0.05
    cini
    0.05
     harde
    0.05
    including
    0.05
    è¿ĩåĪĨ
    0.05
    nern
    0.05
    æīĢ以è¦ģ
    0.05
    Activations Density 0.024%

    No Known Activations