© 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. 56376
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    uga
    -0.10
    annies
    -0.10
    bable
    -0.08
    awning
    -0.08
    cala
    -0.08
    ks
    -0.08
    uras
    -0.08
    AIN
    -0.08
    haus
    -0.08
     Eug
    -0.08
    POSITIVE LOGITS
    sWith
    0.11
    æĹĥ
    0.09
    驼
    0.09
    éĵĽ
    0.09
    è²ī
    0.09
    edly
    0.09
    ered
    0.09
    еÑĩен
    0.09
    梢
    0.08
    ìĹŃ
    0.08
    Activations Density 0.000%

    No Known Activations