© 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. 16766
    Prev
    Next
    INDEX
    Explanations

    model parameters

    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
    iras
    -0.09
    ç±³å°Ķ
    -0.09
    æħİéĩį
    -0.09
    thon
    -0.09
    éĹ°
    -0.09
    edic
    -0.09
    å°¼æĸ¯
    -0.08
    estr
    -0.08
    èĬ³
    -0.08
    formatter
    -0.08
    POSITIVE LOGITS
    èĤī
    0.09
    _AG
    0.09
    ä¼ĺç§ĢçļĦ
    0.09
    æľį
    0.08
     Ranch
    0.08
    éĻµ
    0.08
    æŀī
    0.08
     ranch
    0.08
    exo
    0.08
    åĢ¾åIJij
    0.08
    Activations Density 0.028%

    No Known Activations