© 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. 32113
    Prev
    Next
    INDEX
    Explanations

    subclinical or suboptimal

    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
     оÑĤз
    -0.09
    stoff
    -0.09
    unes
    -0.09
    GenerationStrategy
    -0.09
    DOMContentLoaded
    -0.09
    пп
    -0.09
    ips
    -0.09
    ikki
    -0.08
     Jacobs
    -0.08
    ãĤĤãģ®
    -0.08
    POSITIVE LOGITS
    åĪ«è¯´
    0.09
    å¾Ĺå¾Ī好
    0.09
    çī¹æľīçļĦ
    0.09
    æĺ¯æĪijçļĦ
    0.08
    æ³±
    0.08
    æ¶īåıĬåĪ°
    0.08
    mers
    0.08
     ump
    0.08
    ç»Ļä½łä»¬
    0.08
    ä¸ĸçķĮ第ä¸Ģ
    0.08
    Activations Density 0.042%

    No Known Activations