© 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. 37934
    Prev
    Next
    INDEX
    Explanations

    social networking sites and platforms

    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
    åĬĪ
    -0.09
    ä½İä¼°
    -0.09
    æĮĩ纹
    -0.08
    解èĦ±
    -0.08
    éģ¥è¿ľ
    -0.08
     OB
    -0.08
    æĹģ
    -0.08
    inya
    -0.08
    ä¸ĢéĹ´
    -0.08
    åIJ¬çĿĢ
    -0.08
    POSITIVE LOGITS
     seas
    0.09
    èį¦
    0.08
    .har
    0.08
    社交
    0.08
    åıĻ
    0.08
    osite
    0.08
    åĨįéĢł
    0.08
    çĽ¸äº²
    0.08
    emic
    0.08
    趣
    0.08
    Activations Density 0.068%

    No Known Activations