© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17202
    Prev
    Next
    INDEX
    Explanations

    money laundering, organized crime, 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
     Braves
    -0.07
    åĮ»çĸĹäºĭæķħ
    -0.07
    èĬĴ
    -0.07
    æĢ¥æķij
    -0.07
    anager
    -0.07
    prd
    -0.06
    éĨį
    -0.06
    èĢķ
    -0.06
    ysis
    -0.06
    çĪ±å°Ķ
    -0.06
    POSITIVE LOGITS
    åĽ¢ä¼Ļ
    0.12
     launder
    0.11
     laundering
    0.11
    å«Įçĸij
    0.10
    æ´ĹéĴ±
    0.10
    åı¯çĸij
    0.10
    éģıåĪ¶
    0.10
    æ³ķç½ij
    0.10
    æŁ¥èİ·
    0.09
    çªĿ
    0.09
    Activations Density 0.207%

    No Known Activations