© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 20733
    Prev
    Next
    INDEX
    Explanations

    commercial applications and contexts

    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
    æªĶ
    -0.09
    etically
    -0.09
    mnt
    -0.09
    /if
    -0.09
    olls
    -0.09
    yan
    -0.09
    寺
    -0.08
    chu
    -0.08
    okia
    -0.08
    .nz
    -0.08
    POSITIVE LOGITS
    ization
    0.13
    ised
    0.13
    isation
    0.12
    åĮĸçļĦ
    0.12
    isé
    0.11
    ized
    0.11
    ising
    0.11
    ous
    0.11
    éŀħ
    0.10
    ize
    0.10
    Activations Density 0.028%

    No Known Activations