© 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. 20873
    Prev
    Next
    INDEX
    Explanations

    messages, media, and communication

    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
    arbon
    -0.06
    аÑģÑģа
    -0.06
    æĪijè¿Ļ个
    -0.06
    è¯¥åľ°åĮº
    -0.06
    è°Ī
    -0.06
    æ±Ĥ羣
    -0.06
    æ²Ļæ²Ļ
    -0.05
    repid
    -0.05
    isement
    -0.05
    çļĦåĮºåŁŁ
    -0.05
    POSITIVE LOGITS
    INK
    0.06
    anzo
    0.06
    家åºŃæķĻèĤ²
    0.05
    æµģè¡Į
    0.05
    åĬłéĢŁ
    0.05
    æłª
    0.05
    vangen
    0.05
     soci
    0.05
    anan
    0.05
    åĺ
    0.05
    Activations Density 0.023%

    No Known Activations