© 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. 61212
    Prev
    Next
    INDEX
    Explanations

    Carm, arma, arm

    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
    ly
    -0.10
    جر
    -0.10
    æ³ķ人
    -0.09
    èµĦæºIJæķ´åIJĪ
    -0.09
    ä¹İ
    -0.09
    ä¸įæķ¢
    -0.09
    رار
    -0.09
    ло
    -0.09
    IRO
    -0.09
    çIJĨäºĭä¼ļ
    -0.09
    POSITIVE LOGITS
    fully
    0.13
    æ±ģ
    0.10
    ÅŁÄ±k
    0.09
    è¾ĺ
    0.08
    åħĪæĺ¯
    0.08
    geber
    0.08
    ties
    0.08
    åĬŀåħ¬åİħ
    0.08
    ள
    0.08
    ãģĦãģĨ
    0.08
    Activations Density 0.023%

    No Known Activations