© 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. 7736
    Prev
    Next
    INDEX
    Explanations

    car parts and accessories

    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
    家éŨåı£
    -0.10
    ä¸įæĪIJ
    -0.09
    iceps
    -0.09
    ish
    -0.09
     DEAL
    -0.09
    à¹Ħà¸Ĺ
    -0.09
    liness
    -0.08
    åħ¨ç¤¾ä¼ļ
    -0.08
     lear
    -0.08
    ä¿Ĺ
    -0.08
    POSITIVE LOGITS
    çĦķ
    0.10
    oir
    0.09
    /mit
    0.09
    ylene
    0.09
    oking
    0.09
    è¿Ī
    0.08
    omes
    0.08
    æĭ©
    0.08
    ibi
    0.08
    yu
    0.08
    Activations Density 0.005%

    No Known Activations