© 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. 23192
    Prev
    Next
    INDEX
    Explanations

    smoking cessation and withdrawal

    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
    满满çļĦ
    -0.10
    ä»Ģä¹Īåij¢
    -0.10
    æŀ¢
    -0.10
    ä¸įåħį
    -0.09
     Kn
    -0.09
    èĵij
    -0.08
    coh
    -0.08
    yon
    -0.08
    æīĢåľ¨
    -0.08
    å¦ŀ
    -0.08
    POSITIVE LOGITS
    .sg
    0.11
    èĢ³è¾¹
    0.09
    æ·¡åĮĸ
    0.09
     builtin
    0.09
    bearer
    0.09
    .googlecode
    0.09
    illas
    0.08
    ologic
    0.08
    ORY
    0.08
    éĻĭ
    0.08
    Activations Density 0.022%

    No Known Activations