© 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. 17972
    Prev
    Next
    INDEX
    Explanations

    dating inquiries and advice

    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
    sey
    -0.06
    ساد
    -0.06
    ArrayOf
    -0.06
    /disable
    -0.06
    ãĤĤãĤīãģ£ãģŁ
    -0.06
    大ä¼ļä¸Ĭ
    -0.06
    çĦ¶å¤§
    -0.06
    OLUM
    -0.06
    angkut
    -0.06
    feb
    -0.06
    POSITIVE LOGITS
    åĪ°çļĦ
    0.07
    opper
    0.06
    verse
    0.05
    cast
    0.05
    unk
    0.05
    ãĤĨ
    0.05
    è²
    0.05
    stum
    0.05
    ìļ©
    0.05
    er
    0.05
    Activations Density 0.004%

    No Known Activations