© 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. 36692
    Prev
    Next
    INDEX
    Explanations

    credit and blame assignment

    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
    perimental
    -0.11
    yal
    -0.11
     Alexandra
    -0.08
    lage
    -0.08
     apt
    -0.08
    imenti
    -0.08
    drv
    -0.08
    æīįæĺ¯çľŁæŃ£
    -0.08
    åıijè¨Ģ人
    -0.08
    åįłæľī
    -0.08
    POSITIVE LOGITS
    èµ°è¿Ľ
    0.11
    åĴĦ
    0.10
    åīľ
    0.10
    æ°´åŁŁ
    0.09
    失èIJ½
    0.09
    èµ°åĩºåİ»
    0.09
    æľīä»·åĢ¼
    0.09
    åĮºåŁŁåĨħ
    0.09
    çī¢åĽºæłijç«ĭ
    0.09
    æľīä»·åĢ¼çļĦ
    0.09
    Activations Density 0.013%

    No Known Activations