© 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. 50462
    Prev
    Next
    INDEX
    Explanations

    way to express or determine

    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
    åĬ±
    -0.09
    çī¹åĪ«æĺ¯
    -0.08
    anky
    -0.08
     Regents
    -0.08
    Dur
    -0.08
     dur
    -0.07
    Dou
    -0.07
     Ank
    -0.07
    ÑĢаÑī
    -0.07
    Spread
    -0.07
    POSITIVE LOGITS
    ilde
    0.11
    åIJĦèĩªçļĦ
    0.09
    æĶĺ
    0.09
    ÙĬراÙĨ
    0.09
     Euro
    0.09
    izzy
    0.09
    æĺ¯æĪijçļĦ
    0.09
    ä¸Ģ缴éĥ½
    0.09
    illus
    0.09
    æį
    0.08
    Activations Density 0.246%

    No Known Activations