© 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. 20431
    Prev
    Next
    INDEX
    Explanations

    knowledge representation and data structures

    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
    ยà¹Į
    -0.06
     exerc
    -0.06
    è§Ħå¾ĭçļĦ
    -0.05
    elus
    -0.05
    åĩĨåĪĻ
    -0.05
    è§Ħå¾ĭ
    -0.05
    è¾Ļ
    -0.05
     Criteria
    -0.05
    æĸ°è§Ħå®ļ
    -0.05
    æ¦Ĥ
    -0.05
    POSITIVE LOGITS
    æµİ
    0.06
    aims
    0.06
    declaring
    0.06
    éłĺ
    0.06
     entram
    0.06
    ober
    0.05
    åľ¨ä¹İ
    0.05
    æľ¬åľŁ
    0.05
    سط
    0.05
    ä¸į认è¯Ĩ
    0.05
    Activations Density 0.008%

    No Known Activations