© 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. 58775
    Prev
    Next
    INDEX
    Explanations

    shooting, rifle, and sports

    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
    海绵
    -0.09
    ãĥĥãĤ¯ãĤ¹
    -0.09
    èĪ¹
    -0.08
    豪åįİ
    -0.08
    æŬ
    -0.08
    æ©¡èĥ¶
    -0.08
    annis
    -0.08
    说å®Į
    -0.08
    ä¸ŀ
    -0.08
    alen
    -0.08
    POSITIVE LOGITS
    å°Ħåĩ»
    0.19
    å°Ħ
    0.18
    æŀª
    0.15
     shooting
    0.14
     rifle
    0.14
     Shooting
    0.14
    å°Ħæīĭ
    0.13
     Shot
    0.12
     Rifle
    0.12
     shot
    0.12
    Activations Density 0.110%

    No Known Activations