© 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. 18760
    Prev
    Next
    INDEX
    Explanations

    performance and tuning

    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
    æµģ产
    -0.06
    ä¾ĭ
    -0.06
    ister
    -0.06
    æī¹æ¬¡
    -0.05
    åħģ
    -0.05
     Processing
    -0.05
    æī¹
    -0.05
     processing
    -0.05
    processing
    -0.05
     باÙĦات
    -0.05
    POSITIVE LOGITS
     steigern
    0.06
    ONO
    0.06
    éģı
    0.06
     dahin
    0.06
    .OrderByDescending
    0.06
    åĪĨæŀIJæĬ¥åijĬ
    0.06
    Reduce
    0.06
    å¢ŀæĶ¶
    0.06
     competición
    0.06
    ä¸ĭ课
    0.06
    Activations Density 0.051%

    No Known Activations