© 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. 20900
    Prev
    Next
    INDEX
    Explanations

    provide, offer, receive

    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
    å¼Ħ
    -0.06
    adar
    -0.06
     tát
    -0.06
     renvo
    -0.06
    交å¾ħ
    -0.06
    éļ¾æ±Ĥ
    -0.06
    ä¸įå¿į
    -0.06
    azen
    -0.06
    illah
    -0.06
    hoe
    -0.05
    POSITIVE LOGITS
    ogi
    0.06
    mere
    0.05
    æµģçļĦ
    0.05
    åĴĮç²¾ç¥ŀ
    0.05
    stens
    0.05
     bursts
    0.05
    æµģ
    0.05
    è¿Ļæľ¬
    0.05
    endas
    0.05
     pertinent
    0.05
    Activations Density 0.005%

    No Known Activations