© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8334
    Prev
    Next
    INDEX
    Explanations

    benefit and harm

    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
    寤
    -0.09
     Appeal
    -0.09
    ords
    -0.09
    _singular
    -0.08
    å°ı鸣
    -0.08
     stylist
    -0.08
    (*(
    -0.08
    å¿IJ
    -0.08
    éħįå¥Ĺ
    -0.08
    å®ĺæĸ¹
    -0.08
    POSITIVE LOGITS
     harm
    0.22
    çĽĬ
    0.21
    æľīçĽĬ
    0.19
    åį±å®³
    0.19
    害
    0.18
     Harm
    0.16
    çļĦåį±å®³
    0.16
    åĿıäºĭ
    0.16
    åıĹçĽĬ
    0.16
     beneficial
    0.16
    Activations Density 0.109%

    No Known Activations