© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7209
    Prev
    Next
    INDEX
    Explanations

    FAQ related content

    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
    èĩªæľī
    -0.10
    rys
    -0.09
    pad
    -0.09
    пло
    -0.08
    ä¸Ģå¤Ħ
    -0.08
    社ä¼ļç»Ħç»ĩ
    -0.08
    ãģĹãģ¾ãģĦ
    -0.08
    èĩªé©¾
    -0.08
    ä¸Ģ审
    -0.08
    ä¸įä½Ĩ
    -0.08
    POSITIVE LOGITS
    è¿Ļç§įæĸ¹å¼ı
    0.09
     about
    0.09
    æħ®
    0.09
    çļ±çº¹
    0.09
    éľ¹
    0.09
    äºŃ
    0.08
    æĺİçĻ½äºĨ
    0.08
    æľĪä¸Ń
    0.08
    çª
    0.08
    çĸijéĹ®
    0.08
    Activations Density 0.016%

    No Known Activations