© 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. 19286
    Prev
    Next
    INDEX
    Explanations

    current state or condition

    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
    çľĭä¸į
    -0.07
    è¡Įäºĭ
    -0.06
    ä¸įè¿ľ
    -0.06
    Ø´Ùħ
    -0.06
    resher
    -0.06
    inx
    -0.05
    RAIN
    -0.05
    ä¸Ĭ马
    -0.05
    thinkable
    -0.05
    ger
    -0.05
    POSITIVE LOGITS
    .asset
    0.06
    ora
    0.05
    çģ°å¿ĥ
    0.05
     обÑģÑĥ
    0.05
    æľĢæĸ°çīĪ
    0.05
    ems
    0.05
    åħ¬åijĬå¦Ĥä¸ĭ
    0.05
    ÙİÙijÙħÙİ
    0.05
    éķĸ
    0.05
    ä¸įçŁ¥éģĵä½ł
    0.05
    Activations Density 0.007%

    No Known Activations