© 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. 3466
    Prev
    Next
    INDEX
    Explanations

    proceeds of crime and gains

    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
    çŁ¥éŁ³
    -0.07
     blown
    -0.07
    antan
    -0.07
    绣
    -0.07
    åĨįåĬłåħ¥
    -0.07
    ÑģÑĤан
    -0.06
    å¼ĵ
    -0.06
    çĬ§
    -0.06
     recrut
    -0.06
    DDL
    -0.06
    POSITIVE LOGITS
    å¾ĹåĪ©
    0.10
    æīĢå¾Ĺ
    0.09
     restitution
    0.08
     undes
    0.08
     gains
    0.08
     unjust
    0.08
    /result
    0.08
    çĪ±ä¸įéĩĬæīĭ
    0.08
    åıĹçĽĬ
    0.08
     gain
    0.08
    Activations Density 0.009%

    No Known Activations