© 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. 52976
    Prev
    Next
    INDEX
    Explanations

    viewers and what they perceive

    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
    çŀ½
    -0.11
    ç½®
    -0.10
    ä¸įåħ¬å¹³
    -0.09
    è§ĦèĮĥåĮĸ
    -0.09
    ç»Ħç»ĩé¢Ĩ导
    -0.09
    æīĩ
    -0.09
    åĢĻéĢī
    -0.09
    éĿŀ常æĺİæĺ¾
    -0.08
    渲
    -0.08
    åİĨæŶ
    -0.08
    POSITIVE LOGITS
    çİĩ
    0.11
     Pruitt
    0.09
    åįģä¸ĩ
    0.09
     viewer
    0.09
     viewers
    0.09
    æµģ失
    0.09
    çĽĪ
    0.08
     televis
    0.08
    EMBER
    0.08
    穹
    0.08
    Activations Density 0.017%

    No Known Activations