© 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. 27854
    Prev
    Next
    INDEX
    Explanations

    possession of something illegal

    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
    MEMORY
    -0.09
     hood
    -0.09
    CLUDED
    -0.09
    符
    -0.09
    说æľį
    -0.09
    åĽ¢
    -0.08
     водо
    -0.08
    éĢĢä¼ij
    -0.08
    uma
    -0.08
    urat
    -0.08
    POSITIVE LOGITS
    èį¯
    0.10
     Shr
    0.10
    æ®Ĵ
    0.09
    带æľī
    0.09
    è¿ĻäºĽä¸ľè¥¿
    0.09
    åĥ®
    0.09
    å®īåħ¨éļIJæĤ£
    0.08
    æĭ·
    0.08
    éĥ½è¯´
    0.08
    太å¤ļçļĦ
    0.08
    Activations Density 0.012%

    No Known Activations