© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 38963
    Prev
    Next
    INDEX
    Explanations

    sex partner.sex partner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çIJĨåĮĸ
    -0.07
     Scha
    -0.07
    ug
    -0.06
    rq
    -0.06
    izar
    -0.06
    atr
    -0.06
    robi
    -0.06
    imit
    -0.06
    modern
    -0.06
    lz
    -0.06
    POSITIVE LOGITS
    eses
    0.09
    furt
    0.08
    INGLE
    0.08
    otka
    0.08
    ä¸Ģä¸Ģ
    0.07
    -side
    0.07
    OTO
    0.07
    ÑĢек
    0.07
    对åºĶçļĦ
    0.07
    çĽ¸å¯¹åºĶ
    0.07
    Activations Density 0.017%

    No Known Activations