© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8171
    Prev
    Next
    INDEX
    Explanations

    academic degrees and tracks

    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
    ÑģоÑĤ
    -0.09
     Parade
    -0.08
    annual
    -0.08
     Nobel
    -0.08
    æĬ«
    -0.08
     пен
    -0.08
    mel
    -0.08
    åħħ
    -0.07
    IZE
    -0.07
    èĢĮæĿ¥
    -0.07
    POSITIVE LOGITS
    æĸ¹åIJij
    0.14
    è··
    0.12
    çĪ±å°Ķ
    0.10
    çļĦæĸ¹åIJij
    0.10
    çĪ°
    0.10
     Tracks
    0.09
    çĭ¬ä¸Ģ
    0.09
    à¸Īา
    0.09
    个æĢ§
    0.09
    åĪĨæĺİ
    0.09
    Activations Density 0.061%

    No Known Activations