© 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. 19326
    Prev
    Next
    INDEX
    Explanations

    place names ending with common 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
     cock
    -0.08
    èĻ¹
    -0.08
     stiff
    -0.08
    ãĤį
    -0.08
    æĥ«
    -0.08
    çIJIJ
    -0.08
     Vault
    -0.08
    ør
    -0.08
    Chuck
    -0.08
     vault
    -0.08
    POSITIVE LOGITS
    åĮ»åѦéĻ¢
    0.11
     campus
    0.11
    çłĶ究çĶŁ
    0.10
    å¸ĪèĮĥ
    0.10
     ден
    0.10
    é«ĺæł¡
    0.10
     university
    0.10
    大åѦ
    0.09
    æĤ±
    0.09
     Campus
    0.09
    Activations Density 0.100%

    No Known Activations