© 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. 21134
    Prev
    Next
    INDEX
    Explanations

    available options

    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
    onne
    -0.06
    ius
    -0.06
    缴æİ¥æĪĸ
    -0.06
    sst
    -0.05
     infamous
    -0.05
    umm
    -0.05
    ichten
    -0.05
    ר×Ķ
    -0.05
    usat
    -0.05
    agne
    -0.05
    POSITIVE LOGITS
    lessly
    0.06
    ç¨ĭ度çļĦ
    0.06
    .xlim
    0.06
    Available
    0.05
     Available
    0.05
    -available
    0.05
    inqu
    0.05
    خرة
    0.05
    åı¯çĶ¨çļĦ
    0.05
     Nación
    0.05
    Activations Density 0.010%

    No Known Activations