© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6764
    Prev
    Next
    INDEX
    Explanations

    Carl followed by names

    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
    æĪĸå¤ļ
    -0.11
    zelf
    -0.11
     Äijáo
    -0.10
    ched
    -0.10
    edList
    -0.10
    etro
    -0.10
    versed
    -0.10
    кла
    -0.09
    ilon
    -0.09
    edImage
    -0.09
    POSITIVE LOGITS
    isle
    0.13
    à¹Į
    0.12
    sons
    0.12
    sson
    0.11
    ships
    0.10
    son
    0.10
    é¢ı
    0.10
    bery
    0.10
    è¾ĺ
    0.10
    shaft
    0.09
    Activations Density 0.017%

    No Known Activations