© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20689
    Prev
    Next
    INDEX
    Explanations

    extramarital affairs and relationships

    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
     Jew
    -0.06
    ive
    -0.05
    ä¼¼
    -0.05
    ver
    -0.05
    ht
    -0.05
    å±ķæľĽæľªæĿ¥
    -0.05
     seemingly
    -0.05
     applied
    -0.05
     sor
    -0.05
    attle
    -0.05
    POSITIVE LOGITS
    æ°Ĺãģ«åħ¥ãĤĬãģ®
    0.07
    acerb
    0.06
    anca
    0.06
    opportun
    0.06
     pilota
    0.06
     portf
    0.06
    Represent
    0.06
    åıįåĵį
    0.06
     Rt
    0.06
    eih
    0.06
    Activations Density 0.008%

    No Known Activations