© 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. 18019
    Prev
    Next
    INDEX
    Explanations

    two identical groups

    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
    iene
    -0.06
    ot
    -0.05
    å¤ļ个
    -0.05
     multiple
    -0.05
    åħĪå°Ĩ
    -0.05
    bral
    -0.05
    uple
    -0.05
    engew
    -0.05
    æŃ»
    -0.05
    带çĬ¶
    -0.05
    POSITIVE LOGITS
    اÙħÙĬØ©
    0.06
    ernih
    0.06
    ë¡Ŀ
    0.06
    ilup
    0.06
    ä¼ļåIJĮ
    0.06
    menti
    0.06
    adh
    0.06
    ãģ£ãģĭãĤĬ
    0.06
    æİĴçĥŁ
    0.06
    ç·»
    0.06
    Activations Density 0.101%

    No Known Activations