© 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. 21095
    Prev
    Next
    INDEX
    Explanations

    SQL keywords and identifiers

    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
    çŁŃ
    -0.06
    ró
    -0.06
    åľ³
    -0.05
    çĸİ
    -0.05
     Nov
    -0.05
    çĶŁåĮĸ
    -0.05
    汶
    -0.05
     Wells
    -0.05
    Ïģιν
    -0.05
    çī¹åĪ«è¡ĮæĶ¿åĮº
    -0.05
    POSITIVE LOGITS
    ев
    0.07
    á»ĩ
    0.06
    enty
    0.06
    icidade
    0.06
    æ¡¥éķĩ
    0.06
    appa
    0.06
     corresp
    0.06
    tones
    0.06
    iones
    0.05
    Ñij
    0.05
    Activations Density 0.015%

    No Known Activations