© 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. 21830
    Prev
    Next
    INDEX
    Explanations

    is why

    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
    çĮ¿
    -0.10
    æī°
    -0.09
     Raz
    -0.09
    Processor
    -0.09
    èĤĩ
    -0.09
    åı¨
    -0.08
    åĬ«
    -0.08
    éĺĭ
    -0.08
    processor
    -0.08
    çłĶåıijä¸Ńå¿ĥ
    -0.08
    POSITIVE LOGITS
    è¿Ļå°±æĺ¯
    0.14
    è¿Ļæīįæĺ¯
    0.14
    æīįæĺ¯
    0.11
    æīįæĺ¯çľŁæŃ£
    0.11
    è¬Ĥ
    0.11
    ä»Ģä¹Īåı«
    0.11
     wÅĤaÅĽnie
    0.10
    è°ĵ
    0.10
    羣æŃ£çļĦ
    0.10
    è¿Ļæīį
    0.10
    Activations Density 0.035%

    No Known Activations