© 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. 2643
    Prev
    Next
    INDEX
    Explanations

    mattress covers, king size, shell, waterbed, insert, catheter

    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
    åħħå®ŀ
    -0.09
    åĿIJä¸ĭ
    -0.09
    legg
    -0.09
    æ²Ļåıijä¸Ĭ
    -0.08
    便åı¯
    -0.08
    座ä½į
    -0.08
    ç´¯äºĨ
    -0.08
    кл
    -0.08
    座æ¤ħ
    -0.08
    éģĤ
    -0.08
    POSITIVE LOGITS
    èľĪ
    0.11
     ÐłÐ¾
    0.09
    æŀľåĽŃ
    0.09
    æł¹æºIJ
    0.09
    æĭ¨
    0.08
    æŀľ
    0.08
    tracer
    0.08
    å°Ĭ严
    0.08
    æ®
    0.08
     Slayer
    0.08
    Activations Density 0.036%

    No Known Activations