© 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. 7617
    Prev
    Next
    INDEX
    Explanations

    monitoring systems

    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
    èģŀ
    -0.10
    讪
    -0.10
    stral
    -0.10
    èĥļèĥİ
    -0.09
    Dest
    -0.09
    /animate
    -0.09
    ç²¾è£ħ
    -0.09
    ä¸Ģç»ı
    -0.09
    sut
    -0.09
    éĩįåŀĭ
    -0.09
    POSITIVE LOGITS
    çĽijæݧ
    0.12
    æĬ¥èѦ
    0.12
    çĽijæµĭ
    0.12
    çĽijè§Ĩ
    0.09
     monitoring
    0.09
    brew
    0.09
    åĵ¨
    0.09
    è¿IJç»´
    0.09
    åĨ¶
    0.08
    monitor
    0.08
    Activations Density 0.127%

    No Known Activations