© 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. 36055
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
    ï¸ı
    -0.10
    ạ
    -0.09
    ../
    -0.09
    į
    -0.08
    è®´
    -0.08
    ËIJ
    -0.08
    ogenic
    -0.08
    icular
    -0.08
    obar
    -0.08
    yard
    -0.08
    POSITIVE LOGITS
    mpeg
    0.14
    ignment
    0.10
    ovation
    0.10
    canf
    0.10
    çıij
    0.09
    诮
    0.09
    ached
    0.09
    биÑĤ
    0.09
    åħ¥ãĤĬ
    0.09
    aged
    0.09
    Activations Density 0.237%

    No Known Activations