© 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. 20020
    Prev
    Next
    INDEX
    Explanations

    ACT, AR, MIT, RA, ACE, USE, AD

    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
    éĩįè¦ģæĮĩ示
    -0.06
     Vorm
    -0.06
    åħĪéĶĭ模èĮĥ
    -0.06
    åIJįåѦçĶŁ
    -0.06
    meister
    -0.06
    gte
    -0.06
     اÙĦÙĩا
    -0.05
    å§ĭç¥ĸ
    -0.05
    æ¦Ķ
    -0.05
    ()%
    -0.05
    POSITIVE LOGITS
    è°ĥ
    0.06
    èĦ±
    0.06
     List
    0.06
    端
    0.06
    æĸ¹æ¡Ī
    0.06
     harmon
    0.05
    è¿ĩç¨ĭ
    0.05
    çħĻ
    0.05
    ä¸ĭ车
    0.05
    稳
    0.05
    Activations Density 0.059%

    No Known Activations