© 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. 21440
    Prev
    Next
    INDEX
    Explanations

    public squares and plazas

    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
    à¸Ļวà¸Ļ
    -0.06
    梯度
    -0.06
    éĩijéĴĪ
    -0.06
    ä¸Ģè¯ķ
    -0.06
    abin
    -0.06
    (bits
    -0.06
    ÑĬÑİ
    -0.06
     segreg
    -0.06
    æ¤
    -0.06
    æĢ§ä»·æ¯Ķ
    -0.06
    POSITIVE LOGITS
    å¹¿åľº
    0.07
    å¹¿åľºä¸Ĭ
    0.07
    å»£åł´
    0.06
    iant
    0.05
    æľīåĬĽåľ°
    0.05
    usage
    0.05
     centr
    0.05
     central
    0.05
    éĻĢèŀº
    0.05
     magnitude
    0.05
    Activations Density 0.025%

    No Known Activations