© 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. 20920
    Prev
    Next
    INDEX
    Explanations

    behavioral training and conditioning

    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
     speculative
    -0.07
    åıijçĥ§
    -0.06
    æĥħæĢĢ
    -0.06
     marrow
    -0.06
     coff
    -0.06
     hemat
    -0.06
     half
    -0.06
     ge
    -0.06
    åIJĥåĬĽ
    -0.06
     piercing
    -0.06
    POSITIVE LOGITS
    æݧåĪ¶
    0.10
    å¥ĸæĥ©
    0.10
    /control
    0.09
     behavioral
    0.09
     Rewards
    0.09
    ABA
    0.09
    åĴĮæݧåĪ¶
    0.09
     conditioned
    0.09
    æݧåĪ¶çļĦ
    0.09
    çļĦæݧåĪ¶
    0.09
    Activations Density 0.029%

    No Known Activations