© 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. 20858
    Prev
    Next
    INDEX
    Explanations

    alert and awareness

    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
    yes
    -0.09
    èĪį
    -0.09
    æħ°
    -0.09
    ãĤ¯ãĥ©
    -0.09
    èµ°åĪ°
    -0.08
    ç«ŀ
    -0.08
    acock
    -0.08
    ä¸įå¿į
    -0.08
    dal
    -0.08
    icana
    -0.08
    POSITIVE LOGITS
    èѦæĥķ
    0.24
    èѦ
    0.19
    æŶåĪ»
    0.15
     alert
    0.14
    alert
    0.14
    éļıæŶ
    0.13
     heightened
    0.13
    éĺ²èĮĥ
    0.13
     Alert
    0.12
    å¤ĩæĪĺ
    0.12
    Activations Density 0.069%

    No Known Activations