© 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. 53163
    Prev
    Next
    INDEX
    Explanations

    awards and nominations

    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
    lord
    -0.09
    aket
    -0.09
     ÑģоÑĤÑĢÑĥд
    -0.08
    èµŀæĪIJ
    -0.08
    æģĭæĥħ
    -0.08
    å¤Ń
    -0.08
    失åĪ©
    -0.08
    วร
    -0.08
    sta
    -0.08
    çĥľ
    -0.08
    POSITIVE LOGITS
    èĬ«
    0.10
    ç¼
    0.10
    ä¸ļçķĮ
    0.09
    åħ¼ä»»
    0.09
    Wal
    0.09
     PROFILE
    0.09
     personally
    0.09
    ÑĢÑĥÑĩ
    0.08
    å½ĵéĢī
    0.08
    人çī©
    0.08
    Activations Density 0.052%

    No Known Activations