© 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. 20151
    Prev
    Next
    INDEX
    Explanations

    questions and instructions

    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
    rais
    -0.06
    elp
    -0.06
    ÙĤÙĤ
    -0.05
    okok
    -0.05
    åı°æµ·
    -0.05
    izas
    -0.05
    veille
    -0.05
    試試
    -0.05
    ä¸İ伦
    -0.05
    research
    -0.05
    POSITIVE LOGITS
    ÙĪÙħØ©
    0.06
    adress
    0.05
    umber
    0.05
    صابة
    0.05
    uper
    0.05
    able
    0.05
    èī²
    0.05
    ç«¥åŃIJ
    0.05
    å¹»
    0.05
    uede
    0.05
    Activations Density 0.067%

    No Known Activations