© 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. 50075
    Prev
    Next
    INDEX
    Explanations

    written permission

    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
    æĺ
    -0.09
    èĭŀ
    -0.09
    éĶ¤
    -0.09
    REFERRED
    -0.09
    åĨ¶
    -0.09
    åħļåĨħ
    -0.09
    河西
    -0.08
    precision
    -0.08
    vect
    -0.08
    mani
    -0.08
    POSITIVE LOGITS
    æ´ŀ
    0.11
    æīįè¡Į
    0.11
    åIJ¦åĪĻ
    0.09
    è¦ģä¹Ī
    0.09
     either
    0.09
    åIJ¦åīĩ
    0.09
    cel
    0.09
    ãģĭãģ¤
    0.09
    缸åºĶçļĦ
    0.08
    åı¦è¡Į
    0.08
    Activations Density 0.061%

    No Known Activations