© 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. 19092
    Prev
    Next
    INDEX
    Explanations

    according to

    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
    ibility
    -0.06
    adier
    -0.06
    ieder
    -0.06
     often
    -0.06
    ëĦĪ
    -0.05
    äºĭåĦ¿
    -0.05
    æ¢
    -0.05
    è·¨
    -0.05
    othy
    -0.05
    ä¼¼
    -0.05
    POSITIVE LOGITS
    odom
    0.06
    betrieb
    0.06
    uration
    0.05
    åĬłæĸ¯
    0.05
    åºŁè¯Ŀ
    0.05
     Miser
    0.05
    omma
    0.05
    adors
    0.05
    nist
    0.05
    orre
    0.05
    Activations Density 0.039%

    No Known Activations