© 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. 38507
    Prev
    Next
    INDEX
    Explanations

    pornography

    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
    eksi
    -0.08
    chting
    -0.07
    ä¸ĢæŦ
    -0.07
     Geg
    -0.07
     hust
    -0.07
     retr
    -0.06
    abas
    -0.06
    gett
    -0.06
    ustru
    -0.06
    åt
    -0.06
    POSITIVE LOGITS
    ç¥ŀåħµ
    0.07
    åĬ³
    0.07
    į
    0.07
    oj
    0.07
    ske
    0.07
    ä¸īåı£
    0.07
    onar
    0.07
    reater
    0.07
    åıijåĬ¨
    0.06
    çĶŁçĶŁ
    0.06
    Activations Density 0.104%

    No Known Activations