© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12076
    Prev
    Next
    INDEX
    Explanations

    stalling, stalled, stagnant, stale, halted

    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
    æľīå¿ħè¦ģ
    -0.11
    没æľīå¿ħè¦ģ
    -0.10
    OrElse
    -0.10
    AGER
    -0.09
    ings
    -0.09
    جÙĪ
    -0.09
    Storm
    -0.09
    Ñĥнк
    -0.09
    æıı
    -0.09
    ific
    -0.08
    POSITIVE LOGITS
    åģľæ»ŀ
    0.12
    å±ĢéĿ¢
    0.11
    ç¢Į
    0.10
    è¸Ł
    0.10
    å·²ä¹ħçļĦ
    0.10
    åĭĥ
    0.09
    æ¶Īè´¹
    0.09
    åĭī
    0.09
    太ä¹ħ
    0.09
     chá»Ĺ
    0.09
    Activations Density 0.023%

    No Known Activations