© 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. 19842
    Prev
    Next
    INDEX
    Explanations

    comma followed by words

    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
    luiten
    -0.06
     Watkins
    -0.05
    è¡Ľ
    -0.05
    è±
    -0.05
    KeyName
    -0.05
    ÙĦÙĬا
    -0.05
     Burl
    -0.05
    æı½
    -0.05
    è¿ĺ为
    -0.05
    gados
    -0.05
    POSITIVE LOGITS
    èįī稿
    0.05
    har
    0.05
    并ä¸įèĥ½
    0.05
    帮åĬ©
    0.05
    çļĦæĺ¯
    0.05
     tracks
    0.05
    èį¯çļĦ
    0.05
    没æľīåħ³ç³»
    0.05
     tracked
    0.05
    没åħ³ç³»
    0.05
    Activations Density 0.006%

    No Known Activations