© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36794
    Prev
    Next
    INDEX
    Explanations

    spatial relation

    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
    ลà¸ĩ
    -0.08
    alan
    -0.08
    ivent
    -0.08
    åľ¨äºİ
    -0.08
    åĩºæĿ¥çļĦ
    -0.08
    åľ¨æĪij
    -0.08
    éĿ¢èī²
    -0.08
    ä¸ĭå±ŀ
    -0.08
    çݯå¢ĥä¸ĭ
    -0.08
     Plenty
    -0.08
    POSITIVE LOGITS
    åİ»çľĭçľĭ
    0.10
    ä¸Ģèµ·åİ»
    0.10
    cape
    0.09
    åij½è¿IJ
    0.09
    认åı¯
    0.09
    èĦļæŃ¥
    0.09
    ä¸Ģæŀ¶
    0.09
     него
    0.09
    ä¸Ģå¾ĭ
    0.08
    缸åħ³è§Ħå®ļ
    0.08
    Activations Density 0.048%

    No Known Activations