© 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. 55967
    Prev
    Next
    INDEX
    Explanations

    meet with someone

    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
    该æĢİä¹ĪåĬŀ
    -0.10
    avit
    -0.09
    æĹģ
    -0.09
     patrons
    -0.08
    éĻĩ
    -0.08
    åĽŀéģ¿
    -0.08
    urat
    -0.08
    æŀľ
    -0.08
    æ·»
    -0.08
    æĩĭ
    -0.08
    POSITIVE LOGITS
     завод
    0.09
    æľ¯
    0.08
     lik
    0.08
    аÑĢÑĮ
    0.08
    èģĮä¸ļçĶŁæ¶¯
    0.08
    森
    0.08
    æľīèī²
    0.08
    éĶ®
    0.08
    صÙĨ
    0.08
    æ°Ķè´¨
    0.08
    Activations Density 0.026%

    No Known Activations