© 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. 10809
    Prev
    Next
    INDEX
    Explanations

    concepts like society and corruption

    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
    èµį
    -0.10
    è´Łè´£ä»»
    -0.10
    æ§Ľ
    -0.10
    ç¼Ħ
    -0.09
    èĢģ人家
    -0.09
    åħį责声æĺİ
    -0.09
    ç±į
    -0.08
    LayoutManager
    -0.08
     folded
    -0.08
    _dispatch
    -0.08
    POSITIVE LOGITS
    åģ¶åĥı
    0.13
    åģı离
    0.13
    æŃª
    0.11
    éĤª
    0.10
    åłķ
    0.10
     tÃł
    0.10
    æľī害
    0.10
    çİ·
    0.10
    èİł
    0.10
    æ·«
    0.10
    Activations Density 0.054%

    No Known Activations