© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18225
    Prev
    Next
    INDEX
    Explanations

    speaking, talking, or silent

    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
    ierz
    -0.05
    ovac
    -0.05
    orb
    -0.05
    æ³¢
    -0.05
    æµģæĦŁ
    -0.05
    对æĬĹ
    -0.05
    à¸ķร
    -0.05
    人æĥħ
    -0.05
    åѤ
    -0.05
    å±Ģ
    -0.05
    POSITIVE LOGITS
    æīĢ欲è¨Ģ
    0.07
    å¤ļåĩº
    0.06
    anted
    0.06
    nil
    0.06
    è¾ĵåĩºçļĦ
    0.06
    æĸĹ士
    0.06
    ddb
    0.06
    åĽ¾æĸ¯
    0.06
    论è¯ģ
    0.06
    ç½Ħ
    0.06
    Activations Density 0.018%

    No Known Activations