© 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. 18239
    Prev
    Next
    INDEX
    Explanations

    bilateral

    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
     feud
    -0.06
    轻轻ä¸Ģ
    -0.06
    inkel
    -0.06
    presa
    -0.06
    ÙĦت
    -0.06
    ABCDE
    -0.06
    andia
    -0.06
     Orr
    -0.05
    ä¸Ģ对ä¸Ģ
    -0.05
    å¤īåĮĸ
    -0.05
    POSITIVE LOGITS
    åIJĦ家
    0.07
    åįĥéĩĮ
    0.06
    åįĥ家
    0.05
    estig
    0.05
    åģ¿
    0.05
    mys
    0.05
     espont
    0.05
    اش
    0.05
    è¶ħ
    0.05
    ÙĪØŃ
    0.05
    Activations Density 0.014%

    No Known Activations