© 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. 16970
    Prev
    Next
    INDEX
    Explanations

    disinfect, sterilize, sanitize, iodine

    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
    ograph
    -0.06
    Ø´ØŃ
    -0.06
    inson
    -0.06
    øg
    -0.06
    สิà¸Ļ
    -0.06
    é£ŁçļĦ
    -0.06
    orton
    -0.05
    ÑĤÑĢеннÑıÑı
    -0.05
    æĪĸ许æľī
    -0.05
    OG
    -0.05
    POSITIVE LOGITS
    æ½Ń
    0.06
    è¹Ħ
    0.06
    è¶ķ
    0.06
    æ¶Īæ¯Ĵ
    0.05
    赶
    0.05
    ély
    0.05
     wounds
    0.05
    ehens
    0.05
    epy
    0.05
    done
    0.05
    Activations Density 0.030%

    No Known Activations