© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18411
    Prev
    Next
    INDEX
    Explanations

    credit bureau nominee

    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
    座
    -0.06
    æĿ¥è¯´
    -0.05
    comm
    -0.05
     Phar
    -0.05
    oute
    -0.05
    ÑĬем
    -0.05
    æıIJé«ĺåѦçĶŁ
    -0.05
    cov
    -0.05
     ordinance
    -0.05
    弯弯
    -0.05
    POSITIVE LOGITS
    editable
    0.06
    езд
    0.06
    íĥģ
    0.06
     amal
    0.06
    ä¸Ģå¹´åĨħ
    0.06
     debu
    0.06
    ç³ľ
    0.05
    obra
    0.05
    klus
    0.05
    ischer
    0.05
    Activations Density 0.003%

    No Known Activations