© 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. 17382
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    æ²īçĿĢ
    -0.05
    ing
    -0.05
    خط
    -0.05
    è¿Ļä¸ĢæŃ¥
    -0.05
     strchr
    -0.05
     manual
    -0.05
    opr
    -0.05
     Ñģл
    -0.05
     maneuver
    -0.05
    æĸ¹åIJijåĴĮ
    -0.05
    POSITIVE LOGITS
    ripper
    0.06
    tku
    0.06
    ucar
    0.06
    ذاÙĥ
    0.06
    onestly
    0.06
    asila
    0.06
    cka
    0.06
    /GPL
    0.06
    è¿Ļç§įä¸ľè¥¿
    0.06
    ниÑĨей
    0.06
    Activations Density 0.008%

    No Known Activations