© 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. 21911
    Prev
    Next
    INDEX
    Explanations

    humor and comedy

    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
    ness
    -0.10
    sWith
    -0.10
    omes
    -0.10
    enen
    -0.09
    allel
    -0.09
    unden
    -0.09
    OMEM
    -0.09
    yii
    -0.09
    oris
    -0.09
    y
    -0.08
    POSITIVE LOGITS
    ously
    0.13
    lessly
    0.09
    less
    0.09
    respect
    0.08
    straight
    0.08
    oot
    0.08
    ä¹ĭäºī
    0.08
    izard
    0.08
    ous
    0.08
    .Automation
    0.08
    Activations Density 0.004%

    No Known Activations