© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21426
    Prev
    Next
    INDEX
    Explanations

    neuroscience

    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
    liner
    -0.06
    ocab
    -0.06
    غÙĦ
    -0.06
    社ä¼ļç»ıæµİ
    -0.06
    anova
    -0.05
     babel
    -0.05
     Plain
    -0.05
    untlet
    -0.05
    è¾ħ以
    -0.05
    人åı£
    -0.05
    POSITIVE LOGITS
    åħ¨æģ¯
    0.06
    èļ¤
    0.06
    缸符
    0.06
    天人
    0.05
     aussehen
    0.05
    à¹Īาย
    0.05
    仿çĶŁ
    0.05
    顺åºĶ
    0.05
     sympathy
    0.05
    èŀįåħ¥
    0.05
    Activations Density 0.014%

    No Known Activations