© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8467
    Prev
    Next
    INDEX
    Explanations

    charters and concessions granted

    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¡Į
    -0.11
    éĨī
    -0.09
    å¤ĦåĪĨ
    -0.09
    ä¿¡æģ¯æĬĢæľ¯
    -0.08
    ove
    -0.08
    éķ°
    -0.08
    å®īéĿĻ
    -0.08
    åIJĮåŁİ
    -0.08
     Provid
    -0.08
     sophistic
    -0.08
    POSITIVE LOGITS
    rie
    0.11
    å¹´éĻIJ
    0.10
     monopoly
    0.10
     HT
    0.10
    é¢ģ
    0.10
    çī¹æĿĥ
    0.09
    åŀĦæĸŃ
    0.09
    åĪĽåĬŀ
    0.09
    åĩºç§Ł
    0.09
    åŀĦ
    0.09
    Activations Density 0.066%

    No Known Activations