© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19732
    Prev
    Next
    INDEX
    Explanations

    names after punctuation/prefix

    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
    otle
    -0.07
    Ùħار
    -0.06
    edor
    -0.06
    èĩ´çļĦ
    -0.06
    sar
    -0.06
    ä¸įéĢĢ
    -0.06
    ={"/
    -0.06
    ç¬Ķ
    -0.06
    CLA
    -0.06
    ,/
    -0.05
    POSITIVE LOGITS
    attan
    0.05
    ('/')[-
    0.05
    inden
    0.05
    ä¸Ģ带
    0.05
    nder
    0.05
    æī§å¯¼
    0.05
    èĥ½åĬĽ
    0.05
     particular
    0.05
    æ²¥
    0.05
    int
    0.04
    Activations Density 0.021%

    No Known Activations