© 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. 57391
    Prev
    Next
    INDEX
    Explanations

    sports and media channels

    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
    hti
    -0.10
    Öħ
    -0.09
    inders
    -0.09
    phans
    -0.09
    è¿Ķ乡
    -0.09
    å²ĺ
    -0.09
    sheets
    -0.09
    propri
    -0.09
    lemen
    -0.09
    ung
    -0.08
    POSITIVE LOGITS
    pedia
    0.09
    arium
    0.09
    æľĢåIJİä¸Ģ次
    0.08
    ss
    0.08
    fax
    0.08
    å¼¢
    0.08
    enie
    0.08
    çī¢è®°
    0.08
     ÙħدÙī
    0.08
    -wise
    0.07
    Activations Density 0.270%

    No Known Activations