© 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. 55715
    Prev
    Next
    INDEX
    Explanations

    playing with

    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
    strup
    -0.11
    ä¸Ģ声
    -0.10
    åħľ
    -0.10
    ование
    -0.09
     Gaw
    -0.09
    WAY
    -0.09
     Sund
    -0.09
    è¦ģåİ»
    -0.09
     Singer
    -0.09
    èĥ¼
    -0.09
    POSITIVE LOGITS
    å¼Ħ
    0.11
    ä¸ĢçĤ¹åĦ¿
    0.10
    bers
    0.09
    æŀ¢
    0.08
     forms
    0.08
    å±ĢéĿ¢
    0.08
    ablo
    0.08
    åĪĩãĤĮ
    0.08
    çĪ¹
    0.08
    æĦıåIJij
    0.08
    Activations Density 0.024%

    No Known Activations