© 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. 21478
    Prev
    Next
    INDEX
    Explanations

    enumerating items

    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
    çª
    -0.06
    ä¸įåIJĮç±»åŀĭ
    -0.06
    款车åŀĭ
    -0.05
    è¿ŁæĹ©
    -0.05
    isas
    -0.05
     sorts
    -0.05
     Ñģов
    -0.05
    lott
    -0.05
    对ä¸įåIJĮ
    -0.05
    å¾ĹæĦıçļĦ
    -0.05
    POSITIVE LOGITS
    quer
    0.07
     Autore
    0.06
    åįķ人
    0.06
    otic
    0.06
    ÑģÑĭ
    0.06
    aga
    0.05
    æīĭæĮģ
    0.05
    emplate
    0.05
    裸
    0.05
    为æķ°
    0.05
    Activations Density 0.004%

    No Known Activations