© 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. 17614
    Prev
    Next
    INDEX
    Explanations

    opposing same-sex marriage

    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
    åĦ¿
    -0.05
     sert
    -0.05
     mach
    -0.05
    ÑģкоÑħозÑıй
    -0.05
    uela
    -0.05
     const
    -0.05
    iog
    -0.05
     constit
    -0.05
    çŁ¥è¯Ĩä¸İ
    -0.05
    å¾Ĺè¿ĩ
    -0.05
    POSITIVE LOGITS
    unity
    0.06
    ä»ĺ
    0.06
    ìĸ´ëĤĺ
    0.06
    annot
    0.06
    eree
    0.06
     Ev
    0.05
    attended
    0.05
    basic
    0.05
    ev
    0.05
    indert
    0.05
    Activations Density 0.070%

    No Known Activations