© 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. 18947
    Prev
    Next
    INDEX
    Explanations

    this year's

    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
    anter
    -0.07
    ÙĬات
    -0.06
    -ish
    -0.06
    è·Ŀä»Ĭ
    -0.06
    åºĹéķĩ
    -0.06
    вок
    -0.06
    kori
    -0.06
    è¾¾åħĭ
    -0.06
     Fucking
    -0.06
    åħļå·¥å§Ķ
    -0.05
    POSITIVE LOGITS
    èĬĤçļĦ
    0.06
    endi
    0.05
    ula
    0.05
    /her
    0.05
    cre
    0.05
     arbitrarily
    0.05
     ÑĥÑĩаÑģÑĤи
    0.05
    åĴĮæŶéĹ´
    0.05
    halb
    0.05
    pell
    0.05
    Activations Density 0.052%

    No Known Activations