© 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. 17466
    Prev
    Next
    INDEX
    Explanations

    handling

    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
     fruition
    -0.06
    大çĤ®
    -0.06
    PIP
    -0.06
    benar
    -0.06
     ná»ķ
    -0.06
    ikh
    -0.06
    ussi
    -0.06
    ACHE
    -0.06
    bras
    -0.06
    inka
    -0.06
    POSITIVE LOGITS
    es
    0.05
    urance
    0.05
    éļıæĦı
    0.05
    éĢļçĶ¨çļĦ
    0.05
    st
    0.05
    éļıçĿĢå¹´é¾ĦçļĦå¢ŀéķ¿
    0.05
    éĶ¢
    0.05
    down
    0.05
     anonim
    0.05
    uffer
    0.05
    Activations Density 0.002%

    No Known Activations