© 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. 9115
    Prev
    Next
    INDEX
    Explanations

    disrupt, disruption, balance

    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
    æĺ±
    -0.11
     ngá»Ļ
    -0.10
    麼
    -0.10
    çŀ§
    -0.10
    ongyang
    -0.10
    åij¸
    -0.10
    SETS
    -0.09
    blas
    -0.09
     degraded
    -0.09
    çĿ¢
    -0.09
    POSITIVE LOGITS
    平衡
    0.13
    åİŁæľīçļĦ
    0.12
    æŃ£åľ¨è¿Ľè¡Į
    0.12
    åİŁæľī
    0.12
     plans
    0.11
    æŃ£å¸¸çļĦ
    0.11
     balance
    0.10
    åĿĩè¡¡
    0.10
    åĪĿè¡·
    0.10
     havoc
    0.10
    Activations Density 0.058%

    No Known Activations