© 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. 57919
    Prev
    Next
    INDEX
    Explanations

    dream, dreams, dreaming

    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
    æ´ª
    -0.09
    常年
    -0.09
    _UNIQUE
    -0.08
    isses
    -0.08
     Mushroom
    -0.08
    atura
    -0.08
    anko
    -0.08
    ä¼Ĺ
    -0.08
    Viewport
    -0.08
    èĩªçĦ¶çģ¾å®³
    -0.08
    POSITIVE LOGITS
    梦
    0.13
    夢
    0.13
    梦幻
    0.13
     dream
    0.12
    Ideal
    0.12
    å¯IJ
    0.12
     Dream
    0.11
    æĨ§æĨ¬
    0.11
    Dream
    0.11
    éŃĩ
    0.11
    Activations Density 0.043%

    No Known Activations