© 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. 47501
    Prev
    Next
    INDEX
    Explanations

    looking for

    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
    çĦī
    -0.09
    æłĩåĩĨåĮĸ
    -0.08
    ç³»åĪĹ
    -0.08
     Passing
    -0.08
    Perfect
    -0.08
    isode
    -0.08
    çīĽèĤī
    -0.08
    è¿«
    -0.08
     passing
    -0.08
    äºĨä¸Ģç³»åĪĹ
    -0.08
    POSITIVE LOGITS
     веÑī
    0.10
    éĤ£å°±
    0.09
    羣æŃ£çļĦ
    0.09
     truly
    0.09
    æĦŁåıĹåĪ°
    0.09
    ifference
    0.09
    æĽ´åħ·
    0.08
    Indent
    0.08
    æĽ´èĥ½
    0.08
     Truly
    0.08
    Activations Density 0.029%

    No Known Activations