© 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. 37388
    Prev
    Next
    INDEX
    Explanations

    sports actions

    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
    _HIT
    -0.08
    icide
    -0.08
    ovsky
    -0.08
    stress
    -0.08
    sitemap
    -0.08
    继ç»Ń
    -0.08
    æĪ³
    -0.08
     Prosecutor
    -0.07
    äºĨ解ä¸Ģä¸ĭ
    -0.07
    ancia
    -0.07
    POSITIVE LOGITS
    Ñģад
    0.10
    æ±°
    0.10
    èķĻ
    0.10
    次æķ°
    0.09
    Laugh
    0.09
    ancode
    0.09
    丰ç¡ķ
    0.09
    UNET
    0.09
     recru
    0.09
    åºĶèģĺ
    0.09
    Activations Density 0.001%

    No Known Activations