© 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. 21855
    Prev
    Next
    INDEX
    Explanations

    created

    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
    åĪ©çĶ¨å¥½
    -0.06
    saan
    -0.05
    ermen
    -0.05
     compac
    -0.05
     Hard
    -0.05
     Technik
    -0.05
    Hard
    -0.05
    artisan
    -0.05
     hardest
    -0.05
    lands
    -0.05
    POSITIVE LOGITS
    à¹Īา
    0.06
    åķĨçļĦ
    0.06
    und
    0.06
    stem
    0.06
    stig
    0.06
    å¸ĪçļĦ
    0.06
     Stem
    0.05
    以åѦçĶŁ
    0.05
    urally
    0.05
    jeni
    0.05
    Activations Density 0.001%

    No Known Activations