© 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. 38205
    Prev
    Next
    INDEX
    Explanations

    moral disagreement or relativism

    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
     dedu
    -0.09
    ogui
    -0.09
    yss
    -0.09
    utenberg
    -0.09
     omin
    -0.08
    icode
    -0.08
     favoris
    -0.08
    rypted
    -0.08
    UNET
    -0.08
    rong
    -0.08
    POSITIVE LOGITS
     presup
    0.09
     harms
    0.08
     ought
    0.08
     causal
    0.08
     morally
    0.08
     claims
    0.08
    elic
    0.07
     predicates
    0.07
    ont
    0.07
     Straw
    0.07
    Activations Density 0.134%

    No Known Activations