© 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. 17392
    Prev
    Next
    INDEX
    Explanations

    noum, novo, new

    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
    æĦŁåįģ足
    -0.05
    nop
    -0.05
    ç¥ĸæ¯į
    -0.05
    ×Ļר×ķת
    -0.05
     (__
    -0.05
    agence
    -0.05
    QWidget
    -0.05
    æѦç¥ŀ
    -0.05
     TRANSP
    -0.05
    ç«ŁçĦ¶æĺ¯
    -0.05
    POSITIVE LOGITS
    社
    0.07
    lectron
    0.06
    ione
    0.06
    lieben
    0.06
    ÛĮÙĨÛĮ
    0.05
    viel
    0.05
    大件
    0.05
    conde
    0.05
     kec
    0.05
    elat
    0.05
    Activations Density 0.011%

    No Known Activations