© 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. 10999
    Prev
    Next
    INDEX
    Explanations

    adjectives describing impactful or interesting qualities

    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
    gua
    -0.08
    ulls
    -0.08
     Dw
    -0.08
    Slash
    -0.08
    çĭ®åŃIJ
    -0.08
    ä¹ħä¹ħ
    -0.08
    åħħåĪĨåĪ©çĶ¨
    -0.08
    rij
    -0.08
     wil
    -0.08
    ponent
    -0.07
    POSITIVE LOGITS
    ç¬ı
    0.10
    æľīçĶ¨çļĦ
    0.10
    çļĦçIJĨæĥ³
    0.10
    èĬľ
    0.09
    IKE
    0.09
    æij¸
    0.09
    å¦ĤæľŁ
    0.09
    è±ģ
    0.09
    åĴ¸
    0.09
    趣åij³
    0.09
    Activations Density 0.139%

    No Known Activations