© 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. 29583
    Prev
    Next
    INDEX
    Explanations

    river locations and descriptions

    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
    æĪ¿ä¸ľ
    -0.11
    uda
    -0.10
    reek
    -0.09
    uba
    -0.09
    support
    -0.09
    ä¾
    -0.09
    æĺ§
    -0.09
    ooter
    -0.08
    seller
    -0.08
    umps
    -0.08
    POSITIVE LOGITS
    леÑĩ
    0.11
    çķĶ
    0.10
    亶
    0.10
     Cuomo
    0.09
    boat
    0.09
    dale
    0.09
    banks
    0.09
    дол
    0.09
    ripper
    0.09
    hana
    0.08
    Activations Density 0.035%

    No Known Activations