© 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. 63570
    Prev
    Next
    INDEX
    Explanations

    justice and rights

    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
     вн
    -0.10
    èIJ½åħ¥
    -0.09
    æ²®
    -0.09
    è´Ń
    -0.09
    åĤį
    -0.08
    ç»ıèIJ¥èĢħ
    -0.08
    runner
    -0.08
     Scha
    -0.08
     Tradition
    -0.08
     Fallen
    -0.08
    POSITIVE LOGITS
     justice
    0.14
    æŃ£ä¹ī
    0.14
    åħ¬å¹³
    0.13
     Justice
    0.12
    Justice
    0.12
    justice
    0.12
    åħ¬æŃ£
    0.11
     equity
    0.11
    å¹³çŃī
    0.10
     Equity
    0.10
    Activations Density 0.045%

    No Known Activations