© 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. 7905
    Prev
    Next
    INDEX
    Explanations

    completeness

    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
    ette
    -0.10
    teen
    -0.09
    ield
    -0.09
    ç¾¤å²Ľ
    -0.08
    hap
    -0.08
    ese
    -0.08
    epad
    -0.08
    /or
    -0.08
     discrim
    -0.08
    hm
    -0.08
    POSITIVE LOGITS
    ä¸įäºĨ
    0.15
    zza
    0.14
    æĦıä¹īä¸ĬçļĦ
    0.13
    äºĨä¸Ģç³»åĪĹ
    0.11
    æĦıä¹īä¸Ĭ
    0.11
    主ä¹īèĢħ
    0.10
    äºĨèĩªå·±çļĦ
    0.10
    -bodied
    0.10
    ants
    0.10
    å½»åºķ
    0.10
    Activations Density 0.044%

    No Known Activations