© 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. 17569
    Prev
    Next
    INDEX
    Explanations

    words starting with pre

    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
    uate
    -0.13
    naire
    -0.12
    annes
    -0.10
    lah
    -0.09
    igans
    -0.09
    tat
    -0.09
    gether
    -0.09
    ÙĬات
    -0.09
    为æ°ij
    -0.09
    naires
    -0.09
    POSITIVE LOGITS
    centage
    0.13
    empt
    0.11
    lude
    0.10
    ponder
    0.10
    CEED
    0.10
    emption
    0.10
    åľ°ä¸Ń
    0.10
    å®ļäºĨ
    0.09
    ceed
    0.09
    cept
    0.09
    Activations Density 0.045%

    No Known Activations