© 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. 64030
    Prev
    Next
    INDEX
    Explanations

    Sass, Borg, or dataObjectMapper

    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
    intree
    -0.09
    å¿ĸ
    -0.08
    ittings
    -0.08
    olph
    -0.08
    æķıéĶIJ
    -0.08
    缺åı£
    -0.08
    æŃ£åĽłä¸º
    -0.08
    ederation
    -0.08
    å¹²èĦĨ
    -0.07
    passes
    -0.07
    POSITIVE LOGITS
    .Dto
    0.10
    iana
    0.10
    ening
    0.09
    å¨Ī
    0.09
     Devil
    0.09
    าะ
    0.09
    erator
    0.08
    weed
    0.08
    erior
    0.08
    ä¸ĢåŃĹ
    0.08
    Activations Density 0.001%

    No Known Activations