© 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. 17827
    Prev
    Next
    INDEX
    Explanations

    divorce family law

    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
    éĢı
    -0.08
    yaj
    -0.06
    åĨ¤æŀī
    -0.06
    åIJ¸æĶ¶
    -0.06
    findOrFail
    -0.06
     nạp
    -0.06
     immunity
    -0.06
    exposition
    -0.06
    ronic
    -0.05
    以èĩ³
    -0.05
    POSITIVE LOGITS
    çİ
    0.06
    åĨ³
    0.06
    åĪĨå±ħ
    0.06
     separation
    0.06
    çĵ¢
    0.06
     reun
    0.06
    pren
    0.05
     breakup
    0.05
    åĪĨ离
    0.05
    éĤ£è¾¹çļĦ
    0.05
    Activations Density 0.038%

    No Known Activations