© 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. 6855
    Prev
    Next
    INDEX
    Explanations

    Triple-A affiliation and rankings

    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
    çIJ¢
    -0.10
    éĺŁåijĺ们
    -0.10
    æĬķ稿
    -0.10
    两家
    -0.09
    æīĢå¾Ĺ
    -0.09
     Morse
    -0.09
    ä¿ĿçķĻ
    -0.09
    æ»Ĥ
    -0.09
    pond
    -0.08
    æĭįæĭį
    -0.08
    POSITIVE LOGITS
     Hob
    0.09
    -Jul
    0.09
    ulls
    0.09
    à¹Ģย
    0.09
    éķ¿å¤§äºĨ
    0.09
    ä»»ä½ķæŶåĢĻ
    0.08
    æıĨ
    0.08
    åıijèĤ²
    0.08
    åħ¶æ¬¡
    0.08
     scor
    0.08
    Activations Density 0.150%

    No Known Activations