© 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. 18655
    Prev
    Next
    INDEX
    Explanations

    extract value from file or record

    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
    emand
    -0.07
    ingly
    -0.06
    оÑģÑĤÑĢе
    -0.06
    æĦıä¹ī
    -0.06
    ØŃاÙĦ
    -0.06
    igd
    -0.06
    Äįu
    -0.06
    å¤ļæķ°
    -0.06
     sorts
    -0.06
    (er
    -0.06
    POSITIVE LOGITS
    ellow
    0.06
     queijo
    0.05
    aider
    0.05
    lam
    0.05
    ajes
    0.05
    æľįåĬ¡åĴĮ
    0.05
    Angeb
    0.05
    æľĥæĺ¯
    0.05
    ضÙĬ
    0.05
    aty
    0.05
    Activations Density 0.064%

    No Known Activations