© 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. 20580
    Prev
    Next
    INDEX
    Explanations

    re-election

    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
    áĥķáĥĶ
    -0.05
    gesch
    -0.05
    éĵ¶è¡Įä¿¡çĶ¨åį¡
    -0.05
     scientifically
    -0.05
    toile
    -0.05
    -Semitic
    -0.05
    ieza
    -0.05
    -heart
    -0.05
     ÙħÙĪرد
    -0.05
    æĺİ示
    -0.05
    POSITIVE LOGITS
     tamp
    0.06
     впеÑĢед
    0.06
    è¿Ļ两ç§į
    0.05
    缸åºĶ
    0.05
    isian
    0.05
     rét
    0.05
    <|fim_suffix|>
    0.05
    ambang
    0.05
    æĦıä¹īçļĦ
    0.05
    èĵĿèī²åŃĹä½ĵ
    0.05
    Activations Density 0.026%

    No Known Activations