© 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. 48781
    Prev
    Next
    INDEX
    Explanations

    movies and titles

    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
    åĭ
    -0.10
    iless
    -0.09
    åŁ¹åħ»
    -0.09
    æŁĶæĢ§
    -0.09
    åĦ¿
    -0.09
    åĬĿ
    -0.08
    lek
    -0.08
    alent
    -0.08
    亩
    -0.08
     scouting
    -0.08
    POSITIVE LOGITS
    è¿Ļéĥ¨çĶµå½±
    0.09
    cba
    0.09
    oth
    0.09
    é»ĦçŁ³
    0.09
     Cody
    0.08
    sep
    0.08
    imeo
    0.08
    å¼ıçļĦ
    0.08
    ä¸Ńç§ĭ
    0.08
    å±±åºĦ
    0.08
    Activations Density 0.036%

    No Known Activations