© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5101
    Prev
    Next
    INDEX
    Explanations

    prohibition and prohibited actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ignment
    -0.12
    combe
    -0.11
    iled
    -0.11
    ouce
    -0.10
    驹
    -0.09
    ingle
    -0.09
     ÑĢаÑģположен
    -0.09
    é¬ĵ
    -0.09
    ationship
    -0.09
    ablish
    -0.09
    POSITIVE LOGITS
    ìĤ¬íķŃ
    0.15
    ä½ıäºĨ
    0.11
    lah
    0.10
    ively
    0.10
    ä»»ä½ķ人
    0.10
    ÙĩÙĨ
    0.09
    rack
    0.09
    edly
    0.09
    æĢ§
    0.09
    ê±´
    0.09
    Activations Density 0.038%

    No Known Activations