© 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. 49392
    Prev
    Next
    INDEX
    Explanations

    upset, upsetting, or upsets

    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
    ä¸Ģåī¯
    -0.10
    -quarters
    -0.09
    UMENT
    -0.08
    åģĥ
    -0.08
    utes
    -0.08
     Celebration
    -0.08
    .sg
    -0.08
    uddy
    -0.08
    ged
    -0.08
    å¯Įè´µ
    -0.08
    POSITIVE LOGITS
    ingly
    0.13
    ted
    0.13
    tings
    0.13
    ters
    0.13
    ãĥ¡ãĥ³ãĥĪ
    0.12
    ment
    0.11
    ful
    0.11
    ting
    0.10
    ter
    0.10
    MENT
    0.10
    Activations Density 0.002%

    No Known Activations