© 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. 61626
    Prev
    Next
    INDEX
    Explanations

    qualified or trained professionals

    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
    丢äºĨ
    -0.09
    æĶ¾è¿ĩ
    -0.09
    头çļ®
    -0.08
    åīįä»»
    -0.08
    طاÙĦ
    -0.08
    ä½ķåĨµ
    -0.08
    éĢ¡
    -0.08
    åıĺåĮĸ
    -0.08
    ACHE
    -0.08
    SupportedContent
    -0.08
    POSITIVE LOGITS
    颦
    0.11
    åıĶåıĶ
    0.09
    åĪ°ä½į
    0.09
    ONY
    0.09
     equipped
    0.09
    åĵĴ
    0.09
    衬
    0.09
    eren
    0.09
    çĮ·
    0.09
    à¸Ħà¸Ńย
    0.08
    Activations Density 0.010%

    No Known Activations