© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21600
    Prev
    Next
    INDEX
    Explanations

    vengeful, retributive, payback, reprisal

    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
    ways
    -0.10
    uko
    -0.10
    ä¸ĢåĽ¢
    -0.10
    ä¸ĢéŨ
    -0.09
    çĿĽ
    -0.09
    ized
    -0.08
    abo
    -0.08
    åıªè¦ģæľī
    -0.08
    åĮĸçļĦ
    -0.08
    ampo
    -0.08
    POSITIVE LOGITS
    able
    0.11
    íĴĢ
    0.10
    iveness
    0.10
    enance
    0.10
    ably
    0.10
    apan
    0.10
    nable
    0.09
    ously
    0.09
    оп
    0.09
    IJ
    0.08
    Activations Density 0.004%

    No Known Activations