© 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. 1242
    Prev
    Next
    INDEX
    Explanations

    action verbs

    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
    çī¹åĪ«æĺ¯
    -0.08
    tractive
    -0.08
     AssertionError
    -0.08
    emap
    -0.08
    åIJİèĢħ
    -0.07
    çİ®
    -0.07
    acre
    -0.07
    кÑĥÑģ
    -0.07
    éĽħ
    -0.07
    ching
    -0.07
    POSITIVE LOGITS
    ä¸įäºĨ
    0.12
    edin
    0.10
    äºĨ许å¤ļ
    0.10
    äºĨä¸įå°ij
    0.09
    äºĨ大éĩıçļĦ
    0.09
    æĿ¥è¿ĻéĩĮ
    0.09
    äºĽä»Ģä¹Ī
    0.09
    æ´İ
    0.09
     nevertheless
    0.09
     пÑĢаво
    0.09
    Activations Density 0.954%

    No Known Activations