© 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. 51627
    Prev
    Next
    INDEX
    Explanations

    tendency to

    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
    ç¼Ĺ
    -0.09
    åħ³éĶ®æŶåĪ»
    -0.09
    -fashioned
    -0.09
    acing
    -0.09
    åIJ¬è¯´è¿ĩ
    -0.09
    å®ŀåľ°
    -0.08
    éĿ¢åŃIJ
    -0.08
    涧
    -0.08
    æ¦Ķ
    -0.08
    pine
    -0.08
    POSITIVE LOGITS
    ãĤº
    0.10
    åĢ¾åIJij
    0.09
     awe
    0.09
    à¹Į
    0.09
    Reporting
    0.09
    æĺİæĺ¾çļĦ
    0.09
    ãĤĥ
    0.08
    èĿł
    0.08
    ixel
    0.08
    ities
    0.08
    Activations Density 0.011%

    No Known Activations