© 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. 49683
    Prev
    Next
    INDEX
    Explanations

    this followed by noun

    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
    çĨŁæĤī
    -0.09
    éĤ£å°±æĺ¯
    -0.09
    å¸ĸ
    -0.09
    stab
    -0.09
    æĽ´ä¸º
    -0.09
    ror
    -0.08
    張貼
    -0.08
     Ấ
    -0.08
    å¤ļä½Ļ
    -0.08
    icha
    -0.08
    POSITIVE LOGITS
    è¿ĻäºĽ
    0.11
    éĢĻäºĽ
    0.10
    è¿Ļä¹Īå¤ļ
    0.10
     these
    0.09
    è¿Ļä¹Ī
    0.09
    è½½
    0.09
    these
    0.09
    è¿Ļåĩłä¸ª
    0.09
    æĬĬè¿ĻäºĽ
    0.09
    iant
    0.09
    Activations Density 0.185%

    No Known Activations