© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21301
    Prev
    Next
    INDEX
    Explanations

    intake exhaust combustion engine

    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
    ä»·
    -0.09
    ç¾İè²Į
    -0.09
    èİ·æĤī
    -0.09
    æ·ĭ
    -0.09
    èĭį
    -0.08
    æģĴ
    -0.08
    EMA
    -0.08
     âĢº
    -0.08
    ugg
    -0.08
    errer
    -0.08
    POSITIVE LOGITS
    åĩĨ
    0.10
    antine
    0.09
    abet
    0.09
    æľºæ²¹
    0.09
    PIO
    0.09
    çģ¶
    0.08
    airs
    0.08
    è§ģè¯ģ
    0.08
    åĤħ
    0.08
    为éĩįçĤ¹
    0.08
    Activations Density 0.117%

    No Known Activations