© 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. 17934
    Prev
    Next
    INDEX
    Explanations

    code keywords and 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
    æľīçĹħ
    -0.06
    /OR
    -0.06
     عرض
    -0.06
    åŃĺæľī
    -0.06
    .azure
    -0.06
     razn
    -0.05
    èķ
    -0.05
     conformitÃł
    -0.05
    opportunitÃł
    -0.05
    山海
    -0.05
    POSITIVE LOGITS
    å½±
    0.06
    ÙĪاÙĦ
    0.05
     pil
    0.05
    ee
    0.05
    éĿ¢å¯¹
    0.05
    عÙħÙĦ
    0.05
    çµ®
    0.05
    ç´§æı¡
    0.05
    èѦ
    0.05
    eng
    0.05
    Activations Density 0.012%

    No Known Activations