© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50884
    Prev
    Next
    INDEX
    Explanations

    rad followed by specific suffixes

    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
    lop
    -0.09
    agement
    -0.09
    aec
    -0.09
    çŃ·
    -0.08
    rike
    -0.08
     Bá
    -0.08
    æ´³
    -0.08
    yer
    -0.08
    ì§ij
    -0.08
    loads
    -0.08
    POSITIVE LOGITS
    ically
    0.11
    ureau
    0.10
    ials
    0.10
    ially
    0.10
    ãĤ£
    0.10
    欧å¼ı
    0.09
    .twig
    0.09
    æĹłç§ģ
    0.09
    Disposable
    0.09
    less
    0.09
    Activations Density 0.071%

    No Known Activations