© 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. 5048
    Prev
    Next
    INDEX
    Explanations

    granates, regulation, San Antonio

    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
     Blasio
    -0.09
    西çĵľ
    -0.09
     Schro
    -0.08
    çĮ´åŃIJ
    -0.08
    dee
    -0.08
    Scr
    -0.08
    æľīçļĦ人
    -0.08
    è±Ĩçĵ£
    -0.08
    çĸ£
    -0.08
     Bri
    -0.08
    POSITIVE LOGITS
    agna
    0.10
    gable
    0.09
    azine
    0.09
    æŀģæĺĵ
    0.09
    å¢Ģ
    0.09
     ÑģÑĤен
    0.09
    imestamp
    0.08
    Austin
    0.08
    çīĸ
    0.08
     antis
    0.08
    Activations Density 0.037%

    No Known Activations