© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11046
    Prev
    Next
    INDEX
    Explanations

    badge.com, badge_index, Badge Dale

    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
    à¹Į
    -0.11
    ality
    -0.10
    оÑģÑĮ
    -0.10
    eties
    -0.10
    ally
    -0.10
    ention
    -0.09
    atics
    -0.09
    ide
    -0.09
    ¥
    -0.09
    iske
    -0.09
    POSITIVE LOGITS
    ging
    0.13
    acre
    0.12
    otti
    0.11
    GED
    0.10
    ycl
    0.10
    ourney
    0.10
    enas
    0.09
    åľ¨äº¬
    0.09
    GING
    0.09
    opus
    0.09
    Activations Density 0.006%

    No Known Activations