© 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. 19734
    Prev
    Next
    INDEX
    Explanations

    puzzle and sudoku

    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
    .platform
    -0.06
    iph
    -0.05
    ipro
    -0.05
    åĢŁéī´
    -0.05
    ewa
    -0.05
    اØŃت
    -0.05
    å®°
    -0.05
     compliance
    -0.05
    iliated
    -0.05
    ologne
    -0.05
    POSITIVE LOGITS
    igsaw
    0.07
     crossword
    0.06
    åı¦ä¸ĢåįĬ
    0.06
    Restore
    0.06
    è¬
    0.06
    æݨçIJĨ
    0.06
    paña
    0.05
    Searching
    0.05
    -find
    0.05
    æĭ¼åĽ¾
    0.05
    Activations Density 0.004%

    No Known Activations