© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11344
    Prev
    Next
    INDEX
    Explanations

    locations, authors, or fictional characters

    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
    è¿Ħ
    -0.10
    çļĦçĥŃæĥħ
    -0.09
    ksam
    -0.08
    åĬŀ好
    -0.08
    ç¡®è¯Ĭ
    -0.08
    çĥŃæĥħ
    -0.08
    olvers
    -0.08
    æ³®
    -0.08
    æĪªæŃ¢
    -0.08
    sp
    -0.08
    POSITIVE LOGITS
    ãĢĬ
    0.11
     Bentley
    0.09
    åīįæľŁ
    0.09
    æĨ§æĨ¬
    0.09
    åIJİæľŁ
    0.09
    ç»ĵå°¾
    0.09
    该游æĪı
    0.09
    第ä¸Ģéĥ¨
    0.09
    åIJĪ
    0.09
    åľºæĻ¯
    0.09
    Activations Density 0.112%

    No Known Activations