© 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. 17283
    Prev
    Next
    INDEX
    Explanations

    searching and finding information

    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
    mey
    -0.06
    åĬ¹
    -0.06
    éĢĤå½ĵ
    -0.06
    éĢļè¿ĩå¼Ģå±ķ
    -0.06
    è¿Ľåİ»
    -0.06
    tecz
    -0.06
    ืà¹īà¸Ń
    -0.06
    allocated
    -0.05
    æ·±åħ¥è´¯å½»
    -0.05
    æĭħä»»
    -0.05
    POSITIVE LOGITS
    nun
    0.06
    é»ijæļĹä¸Ń
    0.05
    æļĹ
    0.05
     imaginable
    0.05
    eln
    0.05
    ying
    0.05
    лÑıм
    0.05
     hitch
    0.05
    åİļ
    0.05
     (_,
    0.05
    Activations Density 0.035%

    No Known Activations