© 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. 9253
    Prev
    Next
    INDEX
    Explanations

    pictures, photos, images

    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
    çī¹æ®ĬæĥħåĨµ
    -0.11
    _UTF
    -0.09
    CLU
    -0.09
    å¸ļ
    -0.09
    çŃĶ
    -0.08
    Toy
    -0.08
    imentary
    -0.08
    ulia
    -0.08
    vant
    -0.08
    å¿ĥè·³
    -0.08
    POSITIVE LOGITS
    çħ§çīĩ
    0.19
    åĽ¾çīĩ
    0.18
     images
    0.18
    çļĦçħ§çīĩ
    0.14
    åĽ¾åĥı
    0.14
     photos
    0.14
     pictures
    0.14
     image
    0.14
     photographs
    0.14
    åľĸçīĩ
    0.13
    Activations Density 0.166%

    No Known Activations