© 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. 31979
    Prev
    Next
    INDEX
    Explanations

    vehicles and vessels

    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
    èįīåľ°
    -0.10
    æī©
    -0.09
    ä¼ı
    -0.09
    æŀģ端
    -0.09
    orz
    -0.09
    currentState
    -0.09
    è¿Ļå¥Ĺ
    -0.09
    æĪĺåľºä¸Ĭ
    -0.09
    èĻĵ
    -0.09
     Olson
    -0.09
    POSITIVE LOGITS
    èĪ¹åıª
    0.15
    èĪ¹èĪ¶
    0.12
    èīĺ
    0.11
     vessels
    0.10
    é£ŀæľº
    0.10
    åĪĹ车
    0.10
    大åŀĭ
    0.10
     helicopters
    0.10
    è¿IJè¾ĵ
    0.09
    æĺ¥é£İ
    0.09
    Activations Density 0.128%

    No Known Activations