© 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. 60929
    Prev
    Next
    INDEX
    Explanations

    education qualifications and requirements

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åĵ¥ä¼¦æ¯Ķäºļ
    -0.09
    ä½ı
    -0.09
     dak
    -0.08
    åĤij
    -0.08
    ä¸ĢåĽ¢
    -0.08
     Blond
    -0.08
    ×Ľ×¡
    -0.08
    IVA
    -0.08
    宿èĪį
    -0.08
    åı°
    -0.08
    POSITIVE LOGITS
    注æĺİ
    0.09
    é«ĺçŃīéĻ¢æł¡
    0.09
    Hyper
    0.09
    åĵªæĢķ
    0.09
     Hyper
    0.08
    éģĽ
    0.08
    åħ¶æīĢ
    0.08
    éĢīåıĸ
    0.08
    åѦåīįæķĻèĤ²
    0.08
    é«ĺä¸ŃçĶŁ
    0.08
    Activations Density 0.106%

    No Known Activations