© 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. 20977
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    riques
    -0.07
    دÙħ
    -0.05
     побе
    -0.05
    éľľ
    -0.05
    çĻ»è®°æľºåħ³
    -0.05
    iente
    -0.05
    bÄĻd
    -0.05
     Ab
    -0.05
    hnya
    -0.05
     Abr
    -0.05
    POSITIVE LOGITS
     اÙĨتظار
    0.05
    åĪĴ线
    0.05
    \\.
    0.05
    org
    0.05
    æİ¥åıĹ
    0.05
     (<
    0.05
    isar
    0.05
     parale
    0.05
    \\\\
    0.05
    ÙĪات
    0.05
    Activations Density 0.011%

    No Known Activations