© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35758
    Prev
    Next
    INDEX
    Explanations

    light, lights, lighting

    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
    æ¶ī
    -0.09
    é«Ģ
    -0.09
    å°ıä¼ĻåŃIJ
    -0.09
    éªĭ
    -0.09
    ä¸ĸçķĮä¸Ģæµģ
    -0.08
    åįİå°Ķ
    -0.08
    âĪķ
    -0.08
    åĺ´è§Ĵ
    -0.08
    çĶ³è´Ń
    -0.08
    æłĩæĺİ
    -0.08
    POSITIVE LOGITS
    çģ¯åħī
    0.21
     lights
    0.18
    çģ¯
    0.17
    light
    0.17
    lights
    0.16
     lighting
    0.16
     light
    0.15
    çħ§æĺİ
    0.15
    åħī线
    0.15
    çĩĪ
    0.15
    Activations Density 0.037%

    No Known Activations