© 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. 56874
    Prev
    Next
    INDEX
    Explanations

    New South Wales

    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
    CKER
    -0.10
    овиÑĩ
    -0.10
    á»ij
    -0.10
    æĥĺ
    -0.09
    讹
    -0.09
    è§ŀ
    -0.09
    .Initialize
    -0.09
    legacy
    -0.09
    èĮı
    -0.08
    ä¸ĭ乡
    -0.08
    POSITIVE LOGITS
    éģį
    0.09
    iland
    0.08
    SSIP
    0.08
    รว
    0.08
    -Israel
    0.08
     ÙĪاÙĦع
    0.08
     Cummings
    0.08
    sequences
    0.08
    ibi
    0.08
     discontin
    0.08
    Activations Density 0.149%

    No Known Activations