© 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. 20943
    Prev
    Next
    INDEX
    Explanations

    combining ingredients

    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
    kod
    -0.06
    ologue
    -0.06
    trut
    -0.06
    yvät
    -0.05
     AGAIN
    -0.05
    ç§ijæĸ¯
    -0.05
    incipal
    -0.05
     berdua
    -0.05
    trieb
    -0.05
    éĤ¹
    -0.05
    POSITIVE LOGITS
    足
    0.06
    éĩįéĩij
    0.05
    enticate
    0.05
    à¸ŀล
    0.05
    ÃŃgu
    0.05
    ç²¾
    0.05
    ä½ĵçļĦ
    0.05
    à¹Ħà¸Ķà¹īà¸Ńยà¹Īาà¸ĩà¹Ħร
    0.05
    ä¹ĭçĶ¨
    0.05
    æĺ¾çĿĢ
    0.05
    Activations Density 0.003%

    No Known Activations