© 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. 19332
    Prev
    Next
    INDEX
    Explanations

    Java code examples

    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
    sar
    -0.06
    碧çİī
    -0.05
    缩
    -0.05
    å¿«æį·
    -0.05
    éĢļçĶ¨
    -0.05
    缴æİ¥
    -0.05
    éĽ¹
    -0.05
     наÑģÑĤ
    -0.05
    éĽĨ
    -0.05
    icole
    -0.05
    POSITIVE LOGITS
    设计ä¸Ń
    0.06
    ä¸įèµ°
    0.06
    æķ¬è¯·æľŁå¾ħ
    0.06
    inos
    0.06
    åĩºä¸į
    0.06
    å±ķ示åĩº
    0.06
    ä¸İä¼łç»Ł
    0.06
    åľ¨æŁIJ
    0.06
    æĪĺçķ¥å¸ĥå±Ģ
    0.06
    ugg
    0.05
    Activations Density 0.173%

    No Known Activations