© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9158
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    çĦĻ
    -0.10
    人éĢł
    -0.09
    AAF
    -0.08
    angan
    -0.08
    çĦī
    -0.08
    ç²īå°ĺ
    -0.08
     Lambert
    -0.08
    ì§ľ
    -0.08
    çĻ¾å§ĵ
    -0.08
    èĢķ
    -0.08
    POSITIVE LOGITS
    éĹ®éĹ®
    0.10
    anes
    0.09
    çļĦ缮æłĩ
    0.09
    æľĭ
    0.09
    ä¸Ģçķª
    0.08
    éĢīåĩº
    0.08
     اÙĦØ¥Ùħارات
    0.08
     Ñģп
    0.08
    ickets
    0.08
    åĽłä¸ºæĪij
    0.08
    Activations Density 0.001%

    No Known Activations