© 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. 17200
    Prev
    Next
    INDEX
    Explanations

    possessive noun ('s)

    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
     late
    -0.06
     franca
    -0.05
    edd
    -0.05
    late
    -0.05
    IDAS
    -0.05
     end
    -0.05
     trash
    -0.05
    -0.05
    åĩĨ
    -0.04
    -cap
    -0.04
    POSITIVE LOGITS
    racia
    0.07
     ÙħعÙĨا
    0.06
    rab
    0.06
    Ứ
    0.06
    شرÙĬÙĨ
    0.06
    åħļç»Ħ书记
    0.06
    积æŀģä½ľçĶ¨
    0.06
    åĴĮå¿«ä¹IJ
    0.06
    ä»»ä½ķä¸ľè¥¿
    0.06
    æŶåĪ»åĪ»
    0.06
    Activations Density 0.001%

    No Known Activations