© 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. 19885
    Prev
    Next
    INDEX
    Explanations

    pricing and discounts

    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
    éģĩè§ģ
    -0.10
    æĹłæĦı
    -0.10
    碰
    -0.09
    æĬĵ
    -0.09
    æľ¬æľŁ
    -0.09
     Kend
    -0.09
    æĹ¢æľī
    -0.09
    æĪ¾
    -0.09
    èĭ¥å¹²
    -0.09
    çļĦè·Ŀ离
    -0.09
    POSITIVE LOGITS
    å¿»
    0.09
    åįĩ温
    0.08
    amar
    0.08
    缦
    0.08
    -town
    0.08
    isd
    0.08
     SOS
    0.08
    å±¥èģĮ
    0.08
    姬
    0.08
    %A
    0.08
    Activations Density 0.001%

    No Known Activations