© 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. 51692
    Prev
    Next
    INDEX
    Explanations

    right to information, speech, association, and religion

    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
    ç»ĻäºĨ
    -0.10
    äºĨä¸ĢäºĽ
    -0.09
    éĨĴäºĨ
    -0.09
    äºĨåĩºæĿ¥
    -0.08
    çĽ¸äº²
    -0.08
    èĥ½è®©
    -0.08
    ibaba
    -0.08
    è¯ĥ
    -0.08
    ILLA
    -0.08
    nier
    -0.08
    POSITIVE LOGITS
    æ¯įæł¡
    0.10
    æijĨæĶ¾
    0.10
    追究
    0.09
    享æľī
    0.09
    ç¥ĸåĽ½
    0.09
    åģļ梦
    0.09
    追æ±Ĥ
    0.09
    åĴĤ
    0.09
    orc
    0.09
    涨
    0.09
    Activations Density 0.067%

    No Known Activations