© 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. 51939
    Prev
    Next
    INDEX
    Explanations

    names and citations

    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
    æĶ¯
    -0.09
    æīĵéĢļ
    -0.09
    å°º
    -0.08
    óng
    -0.08
    azi
    -0.08
    .edges
    -0.08
     паÑĢа
    -0.08
    animate
    -0.08
    UGHT
    -0.08
    çĶŁæĢķ
    -0.08
    POSITIVE LOGITS
    è®°å¾Ĺ
    0.09
    åIJİæĤĶ
    0.09
    ç¼Ĩ
    0.08
    åĿļæĮģä¸įæĩĪ
    0.08
    åĴ¬
    0.08
    åİ»åĮ»éĻ¢
    0.08
    æķĻ导
    0.08
    çĶµç¼Ĩ
    0.08
    åį¤
    0.08
    çĶº
    0.08
    Activations Density 0.233%

    No Known Activations