© 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. 55902
    Prev
    Next
    INDEX
    Explanations

    highlights, photos, peek, coverage, record

    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
    æ·±å¤Ħ
    -0.09
    é¹ĥ
    -0.09
    çĭŀ
    -0.09
    æĸ°æĹ¶æľŁ
    -0.09
    ắn
    -0.08
    _binding
    -0.08
     Rosenstein
    -0.08
    è¶ĬæĿ¥è¶Ĭå°ij
    -0.08
    éĶĪ
    -0.08
    åĬĿ
    -0.08
    POSITIVE LOGITS
    äºĭåIJİ
    0.14
    éģĹæĨ¾
    0.12
    åĽŀå¿Ĩ
    0.11
    à¸ļรรยาà¸ģาศ
    0.11
    çķĻä¸ĭäºĨ
    0.11
    æĬ¥éģĵ
    0.11
    åªĴä½ĵæĬ¥éģĵ
    0.11
    çħ§çīĩ
    0.10
    åħ¨ç¨ĭ
    0.10
    延ç»Ń
    0.10
    Activations Density 0.109%

    No Known Activations