© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8747
    Prev
    Next
    INDEX
    Explanations

    issue or grant permits

    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
    漪
    -0.10
    -0.09
    itto
    -0.09
    á»ī
    -0.09
    scape
    -0.09
    liness
    -0.09
    ulist
    -0.08
    å²Ķ
    -0.08
    ä¸Ģç¬Ķ
    -0.08
    ammer
    -0.08
    POSITIVE LOGITS
    ting
    0.10
    tees
    0.10
    æĿ¥èĩª
    0.10
    tee
    0.10
    поÑĢ
    0.10
     annum
    0.10
    ched
    0.09
    BIND
    0.09
    centage
    0.08
    IDD
    0.08
    Activations Density 0.010%

    No Known Activations