© 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. 2183
    Prev
    Next
    INDEX
    Explanations

    that is

    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
    以èĩ´
    -0.10
    èµĸ以çĶŁåŃĺ
    -0.10
    以人为
    -0.09
    imed
    -0.09
    APPED
    -0.09
    ymoon
    -0.09
    åľŃ
    -0.09
    é¾
    -0.09
    [source
    -0.09
    æľŁåĨħ
    -0.09
    POSITIVE LOGITS
    ÑĩаÑĤ
    0.09
    ÑĢам
    0.09
    acios
    0.08
     Brewing
    0.08
    ä¸įçĦ¶
    0.08
    mund
    0.08
    suma
    0.08
    mond
    0.08
    ERENCE
    0.08
    _FMT
    0.08
    Activations Density 0.039%

    No Known Activations