© 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. 19223
    Prev
    Next
    INDEX
    Explanations

    asynchronous function calls

    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
    å®ĥæĺ¯ä¸Ģç§į
    -0.06
    ie
    -0.06
     krijg
    -0.05
    im
    -0.05
    è´¼
    -0.05
    wright
    -0.05
    Ñĥма
    -0.05
    çķĻä¸ĭä¸Ģ
    -0.05
    è·¯éĢı
    -0.05
    ob
    -0.05
    POSITIVE LOGITS
    ernal
    0.07
    åħĥå®Ŀ
    0.07
    ÄĽt
    0.06
    bola
    0.06
    arkan
    0.06
    æīģæ¡ĥ
    0.06
    zysta
    0.06
    伤
    0.06
    agnes
    0.06
    atering
    0.06
    Activations Density 0.007%

    No Known Activations