© 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. 19860
    Prev
    Next
    INDEX
    Explanations

    in charge, in for, in sales, in love, in search

    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
    ópolis
    -0.07
    -lined
    -0.07
    à¸Ļ
    -0.07
    нÑıм
    -0.07
    æ±°
    -0.06
    ÙĬÙĨ
    -0.06
     abr
    -0.06
    nei
    -0.06
    contents
    -0.06
    ä¸Ģ举
    -0.06
    POSITIVE LOGITS
    ع
    0.05
    lach
    0.05
    leich
    0.05
    éĢ±ãģ®
    0.05
    fish
    0.05
    inch
    0.05
    सà¥įथ
    0.05
     setup
    0.05
    space
    0.04
    ëĭ¤
    0.04
    Activations Density 0.010%

    No Known Activations