© 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. 18001
    Prev
    Next
    INDEX
    Explanations

    share with

    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
    åĵģæł¼
    -0.10
    æľįåĬ¡åĮº
    -0.10
    rix
    -0.10
    éĻįåĪ°
    -0.10
    ToEnd
    -0.09
    箬
    -0.09
    åĪ°äºĨ
    -0.09
    è¿Ľåħ¥åĪ°
    -0.09
     dossier
    -0.09
    æĸ°å¨ĺ
    -0.08
    POSITIVE LOGITS
     with
    0.13
     auprès
    0.12
     With
    0.10
     vỼi
    0.10
    with
    0.10
    	with
    0.09
    WithString
    0.09
     against
    0.09
     dengan
    0.09
    é¢ľ
    0.09
    Activations Density 0.124%

    No Known Activations