© 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. 62292
    Prev
    Next
    INDEX
    Explanations

    coolant and fluid levels

    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
    ç½ijåºĹ
    -0.09
    çĤĻ
    -0.09
    èĢ
    -0.09
    éĽªèĬ±
    -0.09
    ä»°
    -0.09
     влаÑģÑĤи
    -0.08
    åIJĬ顶
    -0.08
     вÑĭпÑĥÑģк
    -0.08
    éĢļè¡Įè¯ģ
    -0.08
    æĤ£ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    ä»ĭ
    0.10
    éĻµ
    0.10
    éĩĩ
    0.09
    ãĤ·ãĤ¹ãĥĨãĥł
    0.09
    æŁ³
    0.09
    ä¹ĭ乡
    0.09
    ulia
    0.09
     coolant
    0.08
    寡
    0.08
    åĨ·åį´
    0.08
    Activations Density 0.109%

    No Known Activations