© 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. 51476
    Prev
    Next
    INDEX
    Explanations

    minister for

    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
    ause
    -0.09
    è¿Ļæĺ¯æĪij们
    -0.09
    wear
    -0.09
    chant
    -0.08
    æĬ±åĽ¢
    -0.08
    ìĦ¼íĦ°
    -0.08
    管çIJĨ人åijĺ
    -0.08
    çĭ¬
    -0.08
    secure
    -0.08
    lements
    -0.08
    POSITIVE LOGITS
    éģ£
    0.10
    è´¢æĶ¿éĥ¨
    0.09
     Ao
    0.09
    éĴ®
    0.09
    atta
    0.09
    åģİ
    0.08
    _MB
    0.08
    é¢Ħç®Ĺ
    0.08
    大èĩ£
    0.08
    å±İ
    0.08
    Activations Density 0.147%

    No Known Activations