© 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. 34321
    Prev
    Next
    INDEX
    Explanations

    waste and trash disposal

    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
    ç©¿éĢı
    -0.10
    çIJ¢
    -0.10
    èĢĺ
    -0.10
    ë§ī
    -0.09
    髹
    -0.09
    缴éĢļ车
    -0.09
    åľ¨ä¸Ģ
    -0.09
    触æij¸
    -0.09
    è£ķ
    -0.09
    æ¯Ķåĸ»
    -0.09
    POSITIVE LOGITS
    åŀĥåľ¾
    0.22
     trash
    0.18
    trash
    0.17
    Trash
    0.17
    åŀĥåľ¾åĪĨç±»
    0.15
    åŀĥåľ¾æ¡¶
    0.15
    åŀĥ
    0.15
     Trash
    0.15
    åºŁå¼ĥçī©
    0.14
    -trash
    0.14
    Activations Density 0.074%

    No Known Activations