© 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. 23532
    Prev
    Next
    INDEX
    Explanations

    amateur sex movies

    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
    ene
    -0.07
     dür
    -0.07
    guest
    -0.07
    æĸĽ
    -0.07
    encing
    -0.07
    éĽ¢
    -0.07
    enthal
    -0.06
    ence
    -0.06
    ä¹±
    -0.06
    èī°
    -0.06
    POSITIVE LOGITS
    ãģĹãĤī
    0.09
    0.08
    å¿ĻçļĦ
    0.07
    acct
    0.07
    ç¡®ä¿Ŀ
    0.07
    egram
    0.07
    åĨĽåľ¨
    0.07
    avers
    0.07
    PEAT
    0.07
    åĪ«çľĭ
    0.07
    Activations Density 0.015%

    No Known Activations