© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10088
    Prev
    Next
    INDEX
    Explanations

    office suite or software

    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
    éªĭ
    -0.10
    æľīæĿ¡ä»¶
    -0.10
    åľ°ä¸Ń
    -0.09
    éŨæĪ·
    -0.08
    dag
    -0.08
    rup
    -0.08
    ä¸įåĪ°ä½į
    -0.08
    缯
    -0.08
     Wolves
    -0.08
    alo
    -0.08
    POSITIVE LOGITS
    สà¸Ķ
    0.10
    ocha
    0.10
    -kind
    0.10
    iae
    0.09
    èł¡
    0.09
    ting
    0.09
    phere
    0.08
    keit
    0.08
    wik
    0.08
    owards
    0.08
    Activations Density 0.005%

    No Known Activations