© 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. 52019
    Prev
    Next
    INDEX
    Explanations

    shoot, shot, shoots, shooting

    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
    çĶĺ
    -0.10
    æijĩ头
    -0.09
    æIJĵ
    -0.09
    æĮ¯ãĤĬ
    -0.09
    ä¹Ķ
    -0.09
    etas
    -0.08
    èįĥ
    -0.08
    为主è¦ģ
    -0.08
    轻轻
    -0.08
    EXTERNAL
    -0.08
    POSITIVE LOGITS
    å°Ħåĩ»
    0.17
    å°Ħ
    0.16
     Shoot
    0.12
     shoots
    0.12
     shoot
    0.11
    shoot
    0.11
    Shoot
    0.11
     shots
    0.11
     shot
    0.11
     shooting
    0.11
    Activations Density 0.039%

    No Known Activations