© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20022
    Prev
    Next
    INDEX
    Explanations

    spinning media and spare area

    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
    驱
    -0.11
    ofs
    -0.10
     Wich
    -0.10
    é¾Ľ
    -0.10
    èĮĹ
    -0.10
    ropa
    -0.09
    _renderer
    -0.09
    åĽ½ç½ij
    -0.09
     Rath
    -0.09
    éģĩ
    -0.09
    POSITIVE LOGITS
    俱ä¹IJéĥ¨
    0.10
    æIJŀ
    0.09
    åĸĦ
    0.09
    iti
    0.09
    Club
    0.08
    派人
    0.08
    è¡į
    0.08
    æĭį
    0.08
    nal
    0.08
    Lewis
    0.08
    Activations Density 0.139%

    No Known Activations