© 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. 19397
    Prev
    Next
    INDEX
    Explanations

    code structure punctuation

    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
    ÄĻ
    -0.06
    å¤į
    -0.06
     peine
    -0.05
    гал
    -0.05
    Minor
    -0.05
    åĬ¡
    -0.05
     stappen
    -0.05
    æĸĩåĮĸå¹¿åľº
    -0.05
    ochond
    -0.05
    osaur
    -0.05
    POSITIVE LOGITS
    ness
    0.06
    iveau
    0.06
    è°Ĭ
    0.06
    iono
    0.06
    eea
    0.06
    é©
    0.06
    FU
    0.05
     Insta
    0.05
    oria
    0.05
    overn
    0.05
    Activations Density 0.008%

    No Known Activations