© 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. 18118
    Prev
    Next
    INDEX
    Explanations

    recruiting or seeking sexual partners

    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
    untas
    -0.07
    è·Ŀ
    -0.06
    aros
    -0.06
     revisit
    -0.06
    ç¼ī
    -0.06
     اÙĦÙĥØ«
    -0.06
    izz
    -0.06
    omp
    -0.06
     '{}
    -0.06
    人ä¸Ģ
    -0.06
    POSITIVE LOGITS
    ÙĪاس
    0.06
    inke
    0.06
    ively
    0.05
    iste
    0.05
    SWG
    0.05
     Thanh
    0.05
     skl
    0.05
    äumt
    0.05
     util
    0.05
    æĦıè§ģ
    0.05
    Activations Density 0.001%

    No Known Activations