© 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. 53325
    Prev
    Next
    INDEX
    Explanations

    graduates and alumni

    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
    å¤ĩ
    -0.10
    å¥ij约
    -0.09
    穷人
    -0.09
    çĬį
    -0.09
    ÑĥлÑĮ
    -0.08
    .bn
    -0.08
    addElement
    -0.08
    виз
    -0.08
    åĭ¾
    -0.08
    åIJ¸åħ¥
    -0.08
    POSITIVE LOGITS
    æ¯ķä¸ļåIJİ
    0.16
    æ¯ķä¸ļçĶŁ
    0.16
    æ¯ķä¸ļ
    0.15
    çķ¢æ¥Ń
    0.12
    æł¡åıĭ
    0.12
     graduates
    0.12
    éģįå¸ĥ
    0.12
    åĩºåİ»
    0.12
     alumni
    0.12
    è¾ĵéĢģ
    0.11
    Activations Density 0.064%

    No Known Activations