© 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. 19749
    Prev
    Next
    INDEX
    Explanations

    for ( loop initiations

    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
    osas
    -0.07
     سÙĪÙī
    -0.06
    æĹ¥ä»İ
    -0.06
    gada
    -0.06
    reo
    -0.06
    ÙĪبة
    -0.05
    è°ģéĥ½
    -0.05
    ÑĮми
    -0.05
    å¸ĤéĿ¢ä¸ĬçļĦ
    -0.05
    ÙħÙĴ
    -0.05
    POSITIVE LOGITS
    ates
    0.07
    est
    0.07
    ally
    0.07
    ated
    0.06
    acap
    0.06
    她表示
    0.06
    ites
    0.05
    åħī
    0.05
    ulations
    0.05
    atus
    0.05
    Activations Density 0.020%

    No Known Activations