© 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. 18041
    Prev
    Next
    INDEX
    Explanations

    numbers followed by words or end 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
     Zero
    -0.05
     sensitive
    -0.05
     Äijuá»ķi
    -0.05
    æĭ¿æįı
    -0.05
    orat
    -0.05
    ÑĨова
    -0.05
     ÏĢο
    -0.05
    äºĶèĬ±åħ«
    -0.05
    Äħda
    -0.05
    第äºĮæĿ¡
    -0.05
    POSITIVE LOGITS
    ansch
    0.06
     koÄįi
    0.06
    ancel
    0.06
    .sg
    0.06
    anser
    0.06
    иж
    0.06
     decret
    0.06
    ä¸įåħį
    0.06
    ained
    0.06
    EDGE
    0.06
    Activations Density 0.002%

    No Known Activations