© 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. 52796
    Prev
    Next
    INDEX
    Explanations

    words enclosed in parentheses

    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
    æī¬å°ĺ
    -0.10
    igits
    -0.10
    æĺ¯åľ¨
    -0.09
    aub
    -0.09
    бо
    -0.09
    ä»ĺãģij
    -0.09
    phans
    -0.08
    æĺ¯ä¸Ģ
    -0.08
    让æĤ¨
    -0.08
    phem
    -0.08
    POSITIVE LOGITS
    odore
    0.10
    SourceType
    0.09
    atre
    0.09
    oris
    0.09
    etheless
    0.09
    apel
    0.09
    ych
    0.09
    éĵĽ
    0.09
     tre
    0.08
    iveness
    0.08
    Activations Density 0.266%

    No Known Activations