© 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. 51942
    Prev
    Next
    INDEX
    Explanations

    mirrored words

    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
    ters
    -0.09
    oor
    -0.08
    orre
    -0.08
    å½ĵä¹ĭ
    -0.08
    bing
    -0.08
    wick
    -0.08
    icker
    -0.08
    W
    -0.08
    bow
    -0.08
    thal
    -0.08
    POSITIVE LOGITS
    rors
    0.14
    acles
    0.13
    roring
    0.13
    rored
    0.13
    acle
    0.11
    åħ¬åı¸ç«łç¨ĭ
    0.10
    æł·çļĦ
    0.10
    人åĿĩ
    0.09
    ktor
    0.09
    åĭº
    0.09
    Activations Density 0.027%

    No Known Activations