© 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. 57489
    Prev
    Next
    INDEX
    Explanations

    dreams, nightmares

    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
    诮
    -0.09
    .mit
    -0.09
    缴åįĩ
    -0.09
    éĩĩåıĸ
    -0.09
    åıªå¾Ĺ
    -0.08
    anga
    -0.08
    elas
    -0.08
    è°ĥä¾ĥ
    -0.08
     пÑĢизна
    -0.08
    åĿIJä¸ĭ
    -0.08
    POSITIVE LOGITS
    梦
    0.32
    夢
    0.26
     dream
    0.26
    梦å¢ĥ
    0.26
    梦è§ģ
    0.25
     dreams
    0.23
    dream
    0.22
    梦æĥ³
    0.22
     Dream
    0.21
     Dreams
    0.21
    Activations Density 0.052%

    No Known Activations