© 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. 18849
    Prev
    Next
    INDEX
    Explanations

    code structure containing č

    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
    ç®Ĺ
    -0.05
    reis
    -0.05
    rais
    -0.05
    Ñijл
    -0.05
    èĦ¯
    -0.05
    æĮģ
    -0.05
    åĿĤ
    -0.05
    è§ĦèĮĥ
    -0.05
    rec
    -0.05
    ric
    -0.05
    POSITIVE LOGITS
    isplay
    0.06
    åĴĮæĶ¿çŃĸ
    0.06
    atele
    0.06
    dol
    0.06
     ìĿ´ìĸ´
    0.06
    ãģ®ãģ«
    0.06
    лÑĮÑİ
    0.06
    ona
    0.06
    ãģĿãģĵãģ«
    0.05
    åįĬä»·
    0.05
    Activations Density 0.013%

    No Known Activations