© 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. 8358
    Prev
    Next
    INDEX
    Explanations

    special occasions

    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
    æĹ¶ä»£çļĦ
    -0.10
    paces
    -0.09
    holes
    -0.09
    ish
    -0.09
    åĵ®
    -0.09
    ected
    -0.09
    ðŁı»
    -0.08
    thic
    -0.08
    CSI
    -0.08
    acja
    -0.08
    POSITIVE LOGITS
    als
    0.13
    nel
    0.12
    ä¸įæĺİ
    0.12
    ally
    0.11
    nement
    0.11
    ality
    0.10
    éĻIJãĤĬ
    0.09
    ä¹İ
    0.09
    (stypy
    0.09
    urrences
    0.09
    Activations Density 0.012%

    No Known Activations