© 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
    2. Qwen3.5-4B
    3. 15-RES-MATRYOSHKA-65K
    4. 21918
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
    asma
    -0.07
    ä»Ģä¹ĪåİŁåĽł
    -0.07
    ç»ĵæĿŁæĹ¶
    -0.06
    æķ°åĴĮ
    -0.06
    è·¯åįĹ
    -0.06
    estand
    -0.06
    itial
    -0.06
    eliness
    -0.06
    bish
    -0.06
    kontak
    -0.06
    POSITIVE LOGITS
    s
    0.06
    æ¶īåıĬ
    0.06
    è¿ŀåIJĮ
    0.06
    çIJ¦
    0.05
     equivalent
    0.05
     viewed
    0.05
     involved
    0.05
     interpreted
    0.05
    åħ³äºİ
    0.05
    es
    0.05
    Activations Density 0.002%

    No Known Activations