© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19546
    Prev
    Next
    INDEX
    Explanations

    conjunctions and lists

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.06
     forth
    -0.06
    å°±æ²Ĵæľī
    -0.06
    çŃīä»Ģä¹Ī
    -0.05
    isi
    -0.05
    è¨Ģä¹ĭ
    -0.05
    人åķĬ
    -0.05
     Naast
    -0.05
    ç³»ç»ŁçŃī
    -0.05
    人ä¹ĭ
    -0.05
    POSITIVE LOGITS
    اÙĨÙĩ
    0.08
    ิว
    0.06
     dele
    0.06
    ilege
    0.06
    æ´ĭ
    0.06
    窥
    0.06
    جÙĩ
    0.06
    ufact
    0.06
     CONTRIBUTORS
    0.05
    èĪī
    0.05
    Activations Density 0.052%

    No Known Activations