© 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. 4701
    Prev
    Next
    INDEX
    Explanations

    RUN: commands, verify, emit, namespace

    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
    ÑĢей
    -0.10
    åı°
    -0.09
    /../
    -0.08
    èı½
    -0.08
     Holding
    -0.08
     âĺħ
    -0.08
    祺
    -0.08
    каÑĢÑĤ
    -0.08
    -toggler
    -0.08
     McCart
    -0.08
    POSITIVE LOGITS
    åĮħ容
    0.11
    æŃĮèĪŀ
    0.10
    çĦ¶æĺ¯
    0.09
    çıij
    0.09
     Concurrent
    0.09
    å¹½é»ĺ
    0.09
    tur
    0.09
    ÙĦÙĪÙĨ
    0.08
    äºĽä»Ģä¹Ī
    0.08
    èķĥ
    0.08
    Activations Density 0.417%

    No Known Activations