© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19426
    Prev
    Next
    INDEX
    Explanations

    shooting firearms

    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
    å·¨
    -0.09
    ç»ī
    -0.09
    俳
    -0.08
    èĤ®
    -0.08
    çĪ
    -0.08
    èIJ¥éĢł
    -0.08
    æĭ½
    -0.08
    æ½ľæ°´
    -0.08
    æĽĿ
    -0.07
    ä¸Ń央空è°ĥ
    -0.07
    POSITIVE LOGITS
    èĨĽ
    0.16
    å°Ħåĩ»
    0.15
    æŀª
    0.15
    æ§į
    0.12
    æīĵçĮİ
    0.12
     Firearms
    0.12
    åĻ¨æĿIJ
    0.11
    SHOT
    0.11
     Shooting
    0.11
    ç¼´
    0.11
    Activations Density 0.141%

    No Known Activations