© 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. 18506
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    è²Į
    -0.05
    lect
    -0.05
    lesa
    -0.05
    plom
    -0.05
    ãģªãĤīãģļ
    -0.05
    lott
    -0.05
    ä¼ĺæĥłä»·
    -0.05
    æī¿æİ¥
    -0.05
    ource
    -0.05
    lement
    -0.05
    POSITIVE LOGITS
    anj
    0.06
     Ùħاش
    0.06
     _)
    0.05
    Ñģпи
    0.05
    åºĶçļĦ
    0.05
    æ´
    0.05
    å±Ģ
    0.05
     tiá»ĩn
    0.05
    çŃīçŃī
    0.05
    æĮ¯
    0.05
    Activations Density 0.005%

    No Known Activations