© 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. 4240
    Prev
    Next
    INDEX
    Explanations

    leads/takes her/it to

    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
    ä¼łè¾ĵ
    -0.09
    å£ħ
    -0.09
    å®Īä½ı
    -0.09
    IBE
    -0.09
    çĬį
    -0.09
    ç¡®ä¿Ŀ
    -0.08
    opot
    -0.08
    åŁł
    -0.08
     Cheney
    -0.08
    acon
    -0.08
    POSITIVE LOGITS
    éģįåıĬ
    0.10
    è·ijåĪ°
    0.09
    èĢĮåİ»
    0.09
    侨
    0.09
    åĪ°äºĨ
    0.09
    颦
    0.09
    itle
    0.09
    è£ħç½®
    0.08
    æĢľ
    0.08
    çļĦæĸ¹åIJij
    0.08
    Activations Density 0.038%

    No Known Activations