© 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. 37358
    Prev
    Next
    INDEX
    Explanations

    man-made, anthropogenically, artificial

    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
    ocks
    -0.12
    人身
    -0.10
    à¸Ļำ
    -0.10
     пиÑĤаниÑı
    -0.09
    ocked
    -0.09
    åĮĻ
    -0.09
    çĶ¨é¤IJ
    -0.09
    nic
    -0.09
    anke
    -0.09
    foundation
    -0.09
    POSITIVE LOGITS
    erson
    0.08
    å¨ĺ
    0.08
    ãĤĤãģ®ãģ¯
    0.08
    ely
    0.08
    å§ĭ
    0.08
    åĽłç´ł
    0.08
    à¹ģà¸ŀ
    0.08
    Ñĥни
    0.08
    InThe
    0.08
    PING
    0.08
    Activations Density 0.032%

    No Known Activations