© 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. 57275
    Prev
    Next
    INDEX
    Explanations

    legal and administrative actions

    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
    Ñĥж
    -0.10
    ration
    -0.10
    bidden
    -0.09
    ÑģÑĥд
    -0.09
    åħ·ä½ĵæĥħåĨµ
    -0.09
    бо
    -0.09
    é£Ĵ
    -0.09
    rob
    -0.09
    ho
    -0.09
    åĽŀæĶ¶
    -0.09
    POSITIVE LOGITS
    æµij
    0.10
    éĤ£ä½ł
    0.09
     Shore
    0.08
    å¹²éĥ¨éĺŁä¼į
    0.08
    éĥİ
    0.08
    以人为
    0.08
    æŃ¤é¡¹
    0.07
    æľ¬æĬ¥
    0.07
    她们
    0.07
    å¼ĢæĪ·
    0.07
    Activations Density 0.038%

    No Known Activations