© 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. 19396
    Prev
    Next
    INDEX
    Explanations

    unfairness and injustice

    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
     Deadly
    -0.10
    çĥŁçģ«
    -0.09
     Maur
    -0.09
    onis
    -0.09
    碼
    -0.09
    çĶľç¾İ
    -0.09
    າ
    -0.08
    oger
    -0.08
     Bang
    -0.08
    POSITIVE LOGITS
    ç¯ij
    0.09
    olia
    0.09
    errupt
    0.09
    nable
    0.09
    æįŁå®³
    0.08
    ä¸įåħ¬å¹³
    0.08
    iface
    0.08
    ness
    0.08
    è¯ĺ
    0.08
     injustice
    0.08
    Activations Density 0.006%

    No Known Activations