© 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. 20542
    Prev
    Next
    INDEX
    Explanations

    compiler flags and software names

    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
    èĭ¥å¹²
    -0.06
    âĢ
    -0.06
    ç¥Ŀ
    -0.05
    æľīçļĦ人
    -0.05
     trav
    -0.05
    Âł
    -0.05
     equilibr
    -0.05
    rips
    -0.05
    bahn
    -0.05
    åī§
    -0.05
    POSITIVE LOGITS
    italia
    0.07
    ´Ģ
    0.07
    alse
    0.06
    ALSE
    0.06
    éļĶçĿĢ
    0.06
    ordia
    0.06
    é¢ĹæĺŁ
    0.06
     mỹ
    0.06
    ,double
    0.06
    eel
    0.05
    Activations Density 0.025%

    No Known Activations