© 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. 17706
    Prev
    Next
    INDEX
    Explanations

    programming libraries and frameworks

    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
    udd
    -0.06
     Rov
    -0.06
    à§įবর
    -0.05
    predicted
    -0.05
    å°±å½ĵ
    -0.05
    eper
    -0.05
    obt
    -0.05
    ÑĢÑĥд
    -0.05
    æĭ¥
    -0.05
    rig
    -0.05
    POSITIVE LOGITS
    ä¸Ĭåĵģ
    0.06
    好å¿ĥæĥħ
    0.06
    hattan
    0.06
    å°ıé¢ĺ
    0.06
    ÙĦبة
    0.06
    imal
    0.06
    ãģĦãģŁãģłãģįãģ¾ãģĻ
    0.06
    erness
    0.06
     leftovers
    0.06
    ä¸īåı£
    0.05
    Activations Density 0.075%

    No Known Activations