© 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. 24169
    Prev
    Next
    INDEX
    Explanations

    repelling or expelling

    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
    uments
    -0.11
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    -0.10
    åįĬå¤ľ
    -0.09
    ewise
    -0.09
     appropri
    -0.09
     Belmont
    -0.09
    elper
    -0.09
    åĩłçĤ¹
    -0.08
    opping
    -0.08
     Penal
    -0.08
    POSITIVE LOGITS
    ÑģÑĤвие
    0.10
    éĻŁ
    0.09
    å½ķ
    0.09
    ¬ģ
    0.09
    æĶĺ
    0.09
    ively
    0.08
    uit
    0.08
    çģµåĬ¨
    0.08
    æIJĶ
    0.08
    å¢ħ
    0.08
    Activations Density 0.008%

    No Known Activations