© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34119
    Prev
    Next
    INDEX
    Explanations

    waiting

    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
    æį¢å±Ĭ
    -0.10
    åĭŁéĽĨ
    -0.10
     кÑĢÑĥ
    -0.09
    ener
    -0.09
    éĴ¿
    -0.09
    社ä¼ļ稳å®ļ
    -0.09
    æĭĽæĬķæłĩ
    -0.09
    rips
    -0.09
    è®¤çľŁåŃ¦ä¹ł
    -0.09
    æĪ¿ç§Ł
    -0.09
    POSITIVE LOGITS
    åįĬ天
    0.08
    æīįå¹²
    0.08
    åģļ
    0.08
    .Ct
    0.08
     سبÙĬÙĦ
    0.08
    åºĩ
    0.07
    èĥ½å¾ĹåĪ°
    0.07
     critic
    0.07
     complaint
    0.07
     Nar
    0.07
    Activations Density 0.033%

    No Known Activations