© 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. 17511
    Prev
    Next
    INDEX
    Explanations

    test code contexts

    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
    regel
    -0.06
    åĴĮä¼ĺåĮĸ
    -0.06
     geng
    -0.05
    ÅĦ
    -0.05
    engi
    -0.05
    ç»ĵæŀľæĺ¾ç¤º
    -0.05
    ipan
    -0.05
    çĤ¹å¤ļ
    -0.05
     *__
    -0.05
    ÃģN
    -0.05
    POSITIVE LOGITS
    ity
    0.06
    eil
    0.06
     Jú
    0.06
    rup
    0.06
    æĪijå¿ĥ
    0.05
    é±¼
    0.05
     Government
    0.05
    ONY
    0.05
    è¾¹
    0.05
    ota
    0.05
    Activations Density 0.010%

    No Known Activations