© 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. 8231
    Prev
    Next
    INDEX
    Explanations

    time zones

    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
    æŁ¥çľĭåħ¨æĸĩ
    -0.09
    rew
    -0.09
    åŀŃ
    -0.09
    åĨįè§ģ
    -0.08
    è¿ĽåĨĽ
    -0.08
     peg
    -0.08
    exus
    -0.08
    对ä¸įèµ·
    -0.08
    éħįå¥Ĺ设æĸ½
    -0.08
    tin
    -0.08
    POSITIVE LOGITS
     FITNESS
    0.08
    _REPLY
    0.08
    ç¼Ł
    0.08
    åħ´
    0.08
    arella
    0.08
    Ñĩи
    0.08
    ÏĬ
    0.08
    èĥĥèĤł
    0.08
     Malik
    0.08
    ä¸»å¼ł
    0.08
    Activations Density 0.076%

    No Known Activations