© 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. 16907
    Prev
    Next
    INDEX
    Explanations

    dividing line or row

    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
    è¿ĻäºĽå°ı
    -0.06
    ä½ľåĵģä¸Ń
    -0.06
    mini
    -0.05
     immers
    -0.05
     ÐķÑģÑĤе
    -0.05
    èIJ¥éĢłäºĨ
    -0.05
     иммÑĥниÑĤ
    -0.05
     Mini
    -0.05
    intes
    -0.05
    boh
    -0.05
    POSITIVE LOGITS
    ardia
    0.06
    iggs
    0.06
    inning
    0.06
    angkan
    0.06
    indsay
    0.05
    ç§į
    0.05
    éĩĮ约
    0.05
    они
    0.05
    亨
    0.05
     underlying
    0.05
    Activations Density 0.003%

    No Known Activations