© 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. 21156
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by specific words

    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
    inol
    -0.07
    assa
    -0.06
    æī«ä¸Ģæī«
    -0.06
    Powered
    -0.06
    åįİ缼
    -0.06
    æľīéĻIJ
    -0.06
    eiros
    -0.05
    pires
    -0.05
    åħ¨èĪ¬
    -0.05
    jent
    -0.05
    POSITIVE LOGITS
    èĢĮæĺĵ
    0.05
    å®
    0.05
    á»ķ
    0.05
    least
    0.05
     same
    0.05
    masing
    0.05
     scom
    0.05
    راÙĥ
    0.05
    oh
    0.05
    å¾ĹæĿ¥
    0.05
    Activations Density 0.001%

    No Known Activations