© 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. 19656
    Prev
    Next
    INDEX
    Explanations

    submission and obedience

    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
     ahead
    -0.08
    éļĶ
    -0.07
    æ¦Ĥ
    -0.07
    ahead
    -0.07
     rough
    -0.07
    ä¸į误
    -0.07
    loch
    -0.07
    estern
    -0.07
    éħĿéħ¿
    -0.07
    oen
    -0.07
    POSITIVE LOGITS
    æľįä»İ
    0.13
    ä¹ĸå·§
    0.13
     submissive
    0.13
    åıĹåĪ¶
    0.13
    å±Īæľį
    0.13
    ä¾ĿéĻĦ
    0.13
     dependency
    0.12
     dependence
    0.12
    被åĬ¨
    0.12
    å±Ī
    0.12
    Activations Density 0.142%

    No Known Activations