© 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. 31666
    Prev
    Next
    INDEX
    Explanations

    live coverage and updates

    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
    åĢ¾åIJij
    -0.10
    æıIJè®®
    -0.10
    æıIJæ¡Ī
    -0.09
    æľīéĴĪ对æĢ§
    -0.09
    æľīè¿ĩ
    -0.09
    åĴĮçĿ¦
    -0.09
    çħ¦
    -0.09
    çĶŁæ´»çݯå¢ĥ
    -0.08
    æīĵæĭĽåij¼
    -0.08
     trä
    -0.08
    POSITIVE LOGITS
    å®ŀæŶ
    0.12
     coverage
    0.12
     Coverage
    0.11
     updates
    0.11
    æĬ¥éģĵ
    0.10
    Coverage
    0.10
    _coverage
    0.10
    IAS
    0.10
    updates
    0.10
     reporting
    0.09
    Activations Density 0.191%

    No Known Activations