© 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. 20069
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
    ıra
    -0.06
    ç¿Ĵæħ£
    -0.05
    æľīæŶ
    -0.05
    æĢĿæĥ³æķĻèĤ²
    -0.05
    rtl
    -0.05
    èĭ±æĸĩåŃĹ
    -0.05
    éĢĤåºĶ
    -0.05
    å¿ħé¡»åľ¨
    -0.05
    intendent
    -0.05
    ibun
    -0.05
    POSITIVE LOGITS
    ħ
    0.06
    assis
    0.05
    ÃijA
    0.05
     Than
    0.05
    éģĹæ¼ı
    0.05
     зем
    0.05
     dane
    0.05
    åħijç¾İåħĥ
    0.05
    escu
    0.05
    antaged
    0.05
    Activations Density 0.001%

    No Known Activations