© 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. 4602
    Prev
    Next
    INDEX
    Explanations

    Marx, Engels, dialect

    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
    å°ļ
    -0.10
    æĽĿ
    -0.08
    æī©å»º
    -0.08
    è¡Į为
    -0.08
    åĵį
    -0.08
    ä¿¡èµĸ
    -0.08
    åĵģä½į
    -0.08
     Hub
    -0.08
    æºĸ
    -0.08
    å¹³å®ī
    -0.08
    POSITIVE LOGITS
    åIJĮå¿Ĺ们
    0.14
    马åħĭæĢĿ
    0.14
    åħ±äº§
    0.12
    éĺ¶çº§
    0.12
    çĶŁäº§
    0.12
    çĶŁäº§çĶŁæ´»
    0.11
    工人
    0.11
    åħĭæĢĿ
    0.10
    社ä¼ļåıijå±ķ
    0.10
     dialect
    0.10
    Activations Density 0.071%

    No Known Activations