© 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. 47735
    Prev
    Next
    INDEX
    Explanations

    legal rulings and decisions

    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
     paran
    -0.10
     Bison
    -0.09
    amac
    -0.09
    (extension
    -0.08
     Pars
    -0.08
    pars
    -0.08
    鼶éĥ¨ä»¶
    -0.08
    åĴĮå¹³
    -0.08
     Someone
    -0.08
    æĢĸ
    -0.08
    POSITIVE LOGITS
    /workspace
    0.09
    缺å¸Ń
    0.09
    è§Ĥæij©
    0.09
    Ô½
    0.09
    æĺı
    0.09
    cone
    0.09
    éĺµåľ°
    0.09
    æ²ī
    0.08
    éĻ£
    0.08
    åįĪ
    0.08
    Activations Density 0.201%

    No Known Activations