© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40011
    Prev
    Next
    INDEX
    Explanations

    no [adjective/noun]

    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
    éĤ£äºº
    -0.10
    е
    -0.09
    inki
    -0.09
    æ£īèĬ±
    -0.09
    è¿Ļä¸ĢçĤ¹
    -0.09
     Boxing
    -0.08
    le
    -0.08
    ä¸Ģ身
    -0.08
    çĶ°
    -0.08
    fav
    -0.08
    POSITIVE LOGITS
    çĶŁåij½çļĦ
    0.09
    èݺ
    0.09
    çĤ¬
    0.08
    åħ³äºİæĪij们
    0.08
    æĻº
    0.08
    éģĹçķĻ
    0.08
    -invalid
    0.08
    æĻĭ
    0.08
    åĬ¨éĿĻ
    0.08
    дов
    0.08
    Activations Density 0.017%

    No Known Activations