© 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. 37813
    Prev
    Next
    INDEX
    Explanations

    Sherman, Rodman, car, airport

    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
    arem
    -0.09
    нал
    -0.09
    éĻĢ
    -0.09
    å±ij
    -0.09
    nga
    -0.09
    zzo
    -0.09
    ä¹İ
    -0.08
    åľ°ä¸Ĭ
    -0.08
    emean
    -0.08
    ries
    -0.08
    POSITIVE LOGITS
    ãĤ
    0.10
    edly
    0.09
    er
    0.09
    anal
    0.09
    ä¸Ģè¾Ĩ
    0.09
    äºĨä¸Ģ份
    0.09
    ñana
    0.09
    ä»İ严
    0.08
    ester
    0.08
    iar
    0.08
    Activations Density 0.003%

    No Known Activations