© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20068
    Prev
    Next
    INDEX
    Explanations

    -ization words

    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
    nection
    -0.07
    ated
    -0.07
    交èŃ¦å¤§éĺŁ
    -0.06
    roma
    -0.06
    ärm
    -0.06
    æ¯ĵ
    -0.06
    à¸ĩาà¸Ļ
    -0.06
    æŁļ
    -0.06
    kut
    -0.06
    erva
    -0.06
    POSITIVE LOGITS
     поÑģо
    0.06
    éĩijçŁ³
    0.05
    --
    0.05
    宫éĩĮ
    0.05
    æĢ§æĺ¯
    0.05
    éĺ³åİ¿
    0.05
    çĻ¾åĪĨ
    0.05
    交æµģ
    0.04
    æ¯ĶåĪ©
    0.04
    èģļåľ¨ä¸Ģèµ·
    0.04
    Activations Density 0.008%

    No Known Activations