© 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. 49387
    Prev
    Next
    INDEX
    Explanations

    execute offense, trusting overall

    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
    大人
    -0.10
    çĻ¾äº¿
    -0.07
     lifes
    -0.07
    lenmiÅŁ
    -0.07
    éĻĮ
    -0.07
     stump
    -0.07
    æ»ļçIJĥ
    -0.07
    lashes
    -0.07
    å¥ķ
    -0.07
    æĶ¾è¿ĩ
    -0.07
    POSITIVE LOGITS
    ä¸ĬèµĽåŃ£
    0.13
    èģĮä¸ļçĶŁæ¶¯
    0.13
    çIJĥåijĺ
    0.12
    çIJĥéĺŁ
    0.12
    伤çĹħ
    0.12
    æľ¬åľºæ¯ĶèµĽ
    0.11
    æľ¬èµĽåŃ£
    0.11
    éĺ²å®Ī
    0.11
    çIJĥè¿·
    0.10
    主æķĻç»ĥ
    0.10
    Activations Density 2.888%

    No Known Activations