© 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. 17151
    Prev
    Next
    INDEX
    Explanations

    special characters and programming keywords

    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
    zul
    -0.06
    que
    -0.05
    ueva
    -0.05
    uristic
    -0.05
    vero
    -0.05
     Dice
    -0.05
    pending
    -0.05
    )[:
    -0.05
     oppf
    -0.05
    ·
    -0.05
    POSITIVE LOGITS
     imper
    0.05
    astes
    0.05
    ANO
    0.05
    abet
    0.05
     pikir
    0.05
    å¾Ĺä¸į
    0.05
    ØŃاÙĦ
    0.05
    ohl
    0.05
    adiens
    0.05
    æĢĿæĥ³åĴĮè¡ĮåĬ¨
    0.05
    Activations Density 0.077%

    No Known Activations