© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40406
    Prev
    Next
    INDEX
    Explanations

    slash

    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
    Negative Logits
    åľºæīĢ
    -0.09
    places
    -0.09
     trá»Ŀi
    -0.09
    å§Ķåijĺ
    -0.09
    åĭĥåĭĥ
    -0.09
    place
    -0.09
    eing
    -0.08
    æªĶ
    -0.08
    ropolis
    -0.08
    /classes
    -0.08
    POSITIVE LOGITS
    ../../../
    0.10
    vertisement
    0.09
    ableObject
    0.09
    鸨
    0.09
    omon
    0.09
    imon
    0.09
    nable
    0.09
    èĩªç§ģ
    0.09
    èĪĦ
    0.09
    ioni
    0.08
    Activations Density 0.011%

    No Known Activations