© 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. 22074
    Prev
    Next
    INDEX
    Explanations

    closing code blocks

    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
    ³
    -0.06
    æİ¥åįķ
    -0.06
    inic
    -0.06
    ertility
    -0.05
     _______,
    -0.05
    éĻ°
    -0.05
    æİ¥æĽ¿
    -0.05
    带æľī
    -0.05
    ¾
    -0.05
     Consort
    -0.05
    POSITIVE LOGITS
    èĴĻ
    0.06
     dotted
    0.06
    rack
    0.05
    ropa
    0.05
    Äįuje
    0.05
    åı¯åĪ©çĶ¨
    0.05
     mạo
    0.05
    à¸Ńà¸Ĺ
    0.05
    cott
    0.05
    fest
    0.05
    Activations Density 0.003%

    No Known Activations