© 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. 21932
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
     Major
    -0.06
    Major
    -0.06
    éĽ¢
    -0.06
     major
    -0.05
    离
    -0.05
    amil
    -0.05
    éĹ¹
    -0.05
    ä¸İçİ°å®ŀ
    -0.05
     fronte
    -0.05
    ست
    -0.05
    POSITIVE LOGITS
     néc
    0.06
    бно
    0.06
    éĻĢ
    0.06
    зок
    0.06
    æĿ¿åĴĮ
    0.06
     Tosc
    0.06
    liers
    0.06
     Qaeda
    0.05
    itava
    0.05
    links
    0.05
    Activations Density 0.023%

    No Known Activations