© 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. 58493
    Prev
    Next
    INDEX
    Explanations

    El synagogue names

    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
    ervo
    -0.09
    Successfully
    -0.09
    ordion
    -0.09
    adier
    -0.09
    .Raise
    -0.09
    溶解
    -0.09
    åĽ½å®¶éĩįçĤ¹
    -0.08
    æŁĶ软
    -0.08
     Stern
    -0.08
    纻
    -0.08
    POSITIVE LOGITS
    anken
    0.09
    主å¸Ń
    0.09
    wert
    0.08
    um
    0.08
    thon
    0.08
    bp
    0.07
     пÑĢеп
    0.07
    кл
    0.07
    ugin
    0.07
    妪
    0.07
    Activations Density 0.007%

    No Known Activations