© 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. 53277
    Prev
    Next
    INDEX
    Explanations

    cornerstone of or motto of

    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
    ased
    -0.10
    ä¸ĢæŶ
    -0.09
    ebra
    -0.08
    é£Ļ
    -0.08
    QUOTE
    -0.08
    atto
    -0.08
    ä¸įä¹ħ
    -0.08
    åĪ¶åĵģ
    -0.08
    ieg
    -0.08
    yar
    -0.08
    POSITIVE LOGITS
    ement
    0.09
    ÑĮÑĤе
    0.09
    åij½
    0.09
    们çļĦ
    0.09
    åĿı
    0.08
    ning
    0.08
    hips
    0.08
     xấu
    0.08
    们éĥ½
    0.08
    çIJĨæĥ³çļĦ
    0.08
    Activations Density 0.017%

    No Known Activations