© 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. 31565
    Prev
    Next
    INDEX
    Explanations

    configuration

    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
     Hera
    -0.10
    æĽ´å¤ļä¿¡æģ¯
    -0.09
    itant
    -0.08
    cop
    -0.08
     Bos
    -0.08
    arten
    -0.08
    åĿıäºĭ
    -0.08
    hero
    -0.08
    对æīĭ
    -0.08
     Vimeo
    -0.07
    POSITIVE LOGITS
     configuration
    0.17
     arrangement
    0.14
    configuration
    0.14
    éħįç½®
    0.14
     Configuration
    0.14
    éĺµå®¹
    0.14
     configurations
    0.14
    _configuration
    0.13
    æł¼å±Ģ
    0.12
    Configuration
    0.12
    Activations Density 0.146%

    No Known Activations