© 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. 20804
    Prev
    Next
    INDEX
    Explanations

    Punctuation followed by common sentence starters

    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
    ç´ł
    -0.06
    ç»İ
    -0.06
     Testing
    -0.06
    ave
    -0.06
    issa
    -0.05
    个æķ°
    -0.05
    äºĮ代
    -0.05
     loc
    -0.05
    essional
    -0.05
    人士
    -0.05
    POSITIVE LOGITS
    omos
    0.05
    ä»»
    0.05
    å®ľ
    0.05
    åıĪå¦Ĥä½ķ
    0.05
    å¾Īé«ĺåħ´
    0.05
    åıĪä¸Ģ
    0.05
     пÑĢоиз
    0.05
    åºŁæŃ¢
    0.05
    ANK
    0.05
    jeros
    0.05
    Activations Density 0.373%

    No Known Activations