© 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. 62235
    Prev
    Next
    INDEX
    Explanations

    Google Analytics

    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
     metallic
    -0.10
    糧
    -0.09
    è¯ģ
    -0.09
    交æĺĵä¸Ńå¿ĥ
    -0.09
    .Metadata
    -0.09
    æ¯Ļ
    -0.09
    éĶĪ
    -0.08
    ataka
    -0.08
    ç²¾éĢī
    -0.08
    mere
    -0.08
    POSITIVE LOGITS
    enty
    0.10
    åł±
    0.08
    涣
    0.08
    æ»ļ
    0.08
    utes
    0.08
     Channels
    0.08
     Analytics
    0.08
     Corm
    0.08
    建
    0.08
    вен
    0.07
    Activations Density 0.113%

    No Known Activations