© 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. 6542
    Prev
    Next
    INDEX
    Explanations

    pool

    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
    stell
    -0.10
    áĥ¨
    -0.09
    eo
    -0.09
    éĢģåĩº
    -0.09
    INAL
    -0.09
    Wik
    -0.08
    èĩ³ä¸Ĭ
    -0.08
     streak
    -0.08
    å¢ĥ
    -0.08
     Salv
    -0.08
    POSITIVE LOGITS
     pool
    0.13
    .Pool
    0.13
    (pool
    0.13
    æ±ł
    0.13
     pools
    0.12
     Pool
    0.10
    .pool
    0.10
    æ´¼
    0.09
    æ¾Ħæ¸ħ
    0.09
    游泳
    0.09
    Activations Density 0.050%

    No Known Activations