© 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. 49263
    Prev
    Next
    INDEX
    Explanations

    Perry or Sara

    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
    orem
    -0.09
    enance
    -0.09
    磶
    -0.09
    elect
    -0.09
    sic
    -0.09
    olon
    -0.09
    /or
    -0.09
    åŃ¦å®¶
    -0.09
    etime
    -0.09
    íģ¼
    -0.09
    POSITIVE LOGITS
    ../../../
    0.13
    ience
    0.12
    ities
    0.10
    centage
    0.10
    ãĤī
    0.09
    æĿ¼
    0.09
     addCriterion
    0.09
    èĩ¾
    0.09
     ÑħоÑĤÑı
    0.09
    /lic
    0.09
    Activations Density 0.005%

    No Known Activations