© 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. 20586
    Prev
    Next
    INDEX
    Explanations

    permission and agreement

    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
    uide
    -0.09
    eway
    -0.09
    ouro
    -0.09
    éªł
    -0.09
     gilt
    -0.09
    esso
    -0.09
    让å®ĥ
    -0.09
    çĪ·
    -0.08
    åĩºéģĵ
    -0.08
    éģĩä¸Ĭ
    -0.08
    POSITIVE LOGITS
    æĮº
    0.11
    æĪ¿
    0.09
     ва
    0.08
     Pir
    0.08
    èĥ½å¾ĹåĪ°
    0.08
    è£ħåį¸
    0.08
    ActionResult
    0.08
    æĿŃ
    0.08
    gen
    0.08
    ç«ĭæĸ¹
    0.08
    Activations Density 0.079%

    No Known Activations