© 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. 7880
    Prev
    Next
    INDEX
    Explanations

    fast food chains and brands

    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
    æĴĩ
    -0.09
    antic
    -0.09
    åĪ°æľŁ
    -0.08
    为主è¦ģ
    -0.08
    qed
    -0.08
    æĿŁ
    -0.08
    æĽ¦
    -0.08
    æľŁ
    -0.08
    azi
    -0.08
    &&(
    -0.08
    POSITIVE LOGITS
    utan
    0.10
    Æ°a
    0.10
    å¹²åĩĢ
    0.10
    pass
    0.09
    éĶ»çĤ¼
    0.09
    ãĥªãĤ¢
    0.09
    éľ²åĩº
    0.08
    ears
    0.08
    stro
    0.08
    piece
    0.08
    Activations Density 0.004%

    No Known Activations