© 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. 814
    Prev
    Next
    INDEX
    Explanations

    PC parts and overclocking

    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
    è¨Ĺ
    -0.12
    æIJĶ
    -0.12
    rowsers
    -0.09
    大ä¼Ĺ
    -0.09
    æīĺ
    -0.09
    è§Ħ
    -0.09
    KI
    -0.09
    æĬł
    -0.09
    ippy
    -0.09
    æķ£æŃ¥
    -0.08
    POSITIVE LOGITS
    ifu
    0.11
    èİĺ
    0.09
    ê¶ģ
    0.09
    鼳
    0.09
    æ½Ń
    0.08
    èĢķ
    0.08
    .Atomic
    0.08
    ç»Īæŀģ
    0.08
    รห
    0.08
     JSONObject
    0.08
    Activations Density 0.017%

    No Known Activations