© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 7744
    Prev
    Next
    INDEX
    Explanations

    running software or operations

    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
    åģļå¾Ĺ
    -0.11
    çļĦåŃĺåľ¨
    -0.10
     Scha
    -0.09
    å°ĺ
    -0.09
    ately
    -0.09
    ç£ķ
    -0.09
    æį¢äºĨ
    -0.09
    è§Ĥå½±
    -0.09
    çĭĹ
    -0.09
    认æ¸ħ
    -0.09
    POSITIVE LOGITS
    nings
    0.13
    estone
    0.11
    nable
    0.10
    NING
    0.08
    âĹ»
    0.08
    olon
    0.08
    çĭIJ
    0.08
    æ¼¾
    0.08
    弥补
    0.08
    InBackground
    0.08
    Activations Density 0.173%

    No Known Activations