© 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. 18975
    Prev
    Next
    INDEX
    Explanations

    for more information

    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
    åķ¦
    -0.08
    ologies
    -0.07
    èĮ¶
    -0.07
    å¥ł
    -0.07
    æIJģ
    -0.07
    ard
    -0.07
    åŁºæľ¬åİŁåĪĻ
    -0.07
     shel
    -0.07
    cla
    -0.07
    idon
    -0.07
    POSITIVE LOGITS
    æĽ´å¤ļä¿¡æģ¯
    0.12
    äºĨè§£æĽ´å¤ļ
    0.12
    _RPC
    0.10
    请èģĶç³»
    0.10
    å°¾
    0.10
     اÙĦÙħزÙĬد
    0.10
    ฤ
    0.10
    /rand
    0.10
    èģĶç³»çĶµè¯Ŀ
    0.10
    æĬij
    0.10
    Activations Density 0.013%

    No Known Activations