© 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. 5457
    Prev
    Next
    INDEX
    Explanations

    brutal actions and events

    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
    oret
    -0.10
    Ñģ
    -0.09
    ularity
    -0.09
    gratis
    -0.08
    аÑĤелÑĮ
    -0.08
    Ùħد
    -0.08
    earch
    -0.08
    ey
    -0.08
    ivers
    -0.08
    uilder
    -0.08
    POSITIVE LOGITS
    ized
    0.13
    æĹłæ¯Ķ
    0.13
    ly
    0.11
     honesty
    0.11
    izing
    0.11
    ä¸įç®¡ä½ł
    0.10
    æĹłæĥħ
    0.10
    æĦİ
    0.10
    ize
    0.10
     honest
    0.10
    Activations Density 0.004%

    No Known Activations