© 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. 21687
    Prev
    Next
    INDEX
    Explanations

    drug interactions

    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
    sert
    -0.07
    åı²
    -0.06
    èĩªçĦ¶
    -0.06
    اÛĮÙĦ
    -0.06
    ÑģÑĤоÑĢ
    -0.05
    ارÙĬØ®
    -0.05
     regress
    -0.05
     ov
    -0.05
    æ¶ķ
    -0.05
    geschichte
    -0.05
    POSITIVE LOGITS
     nhau
    0.07
     обо
    0.06
     mutual
    0.06
    åĦ¿
    0.05
    coop
    0.05
    äºĴ为
    0.05
     بعضÙĩا
    0.05
    каÑģ
    0.05
    缸å¤Ħ
    0.05
     combinations
    0.05
    Activations Density 0.045%

    No Known Activations