© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21927
    Prev
    Next
    INDEX
    Explanations

    job candidates

    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
    大æĪ·
    -0.09
    交éĢļå·¥åħ·
    -0.09
    æij¸
    -0.09
    å¾Īå°ı
    -0.08
    éŵ
    -0.07
    åĮħåĽ´
    -0.07
    ç¼ģ
    -0.07
    æijĨ
    -0.07
    å±ķåĩº
    -0.07
    碰åĪ°
    -0.07
    POSITIVE LOGITS
    æ¸ħæī«
    0.10
    è¸ıåħ¥
    0.09
    æĹ¢æľī
    0.09
    .pid
    0.09
     nic
    0.09
    æľĿ
    0.09
    abinet
    0.09
    符åIJĪ
    0.09
    Rail
    0.09
    çĶ³è¯·
    0.09
    Activations Density 0.061%

    No Known Activations