© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 58670
    Prev
    Next
    INDEX
    Explanations

    Parker

    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
    и
    -0.11
    oris
    -0.10
    nik
    -0.10
    liner
    -0.10
    rical
    -0.10
    身价
    -0.09
    é¡į
    -0.09
    ive
    -0.09
    egers
    -0.09
    entifier
    -0.09
    POSITIVE LOGITS
     indis
    0.09
    AGON
    0.09
    à¹Ģà¸Ńà¸ĩ
    0.08
    å¾Ĺä½ı
    0.08
    ä¸ĬçıŃæĹı
    0.08
     ÑģамоÑģÑĤоÑı
    0.08
    -out
    0.08
    /or
    0.08
    å»ī
    0.08
     BMC
    0.08
    Activations Density 0.004%

    No Known Activations