© 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. 57067
    Prev
    Next
    INDEX
    Explanations

    learn or reinforce

    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
    eroy
    -0.09
    endas
    -0.08
    ç½ijåıĭè¯Ħ论
    -0.08
    éĥ½æĺ¯èĩªå·±
    -0.08
    Injected
    -0.08
    ç¿°
    -0.07
    _PRIVATE
    -0.07
    åĴĮä¸ĸçķĮ
    -0.07
    ippo
    -0.07
    ãĥ¼ãĤ¯
    -0.07
    POSITIVE LOGITS
    éĶ¦ä¸Ĭæ·»èĬ±
    0.10
    è¿Ľä¸ĢæŃ¥å¼ºåĮĸ
    0.10
     reinforce
    0.10
     reinforcing
    0.10
    强åĮĸ
    0.10
     reinforces
    0.09
     reinforcement
    0.09
    è¿Ľä¸ĢæŃ¥æĺİç¡®
    0.09
     further
    0.09
     ê°ķíĻĶ
    0.09
    Activations Density 0.180%

    No Known Activations