© 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. 56558
    Prev
    Next
    INDEX
    Explanations

    places like theaters, shops, schools

    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
    ä»ĸä»¬åľ¨
    -0.11
    ä¹ĭ乡
    -0.10
    æĪĸå¤ļ
    -0.09
    没è§ģè¿ĩ
    -0.09
     Eh
    -0.09
    èĽ¤
    -0.09
    endid
    -0.09
    建档
    -0.09
    åı¸
    -0.08
    åī§ç»Ħ
    -0.08
    POSITIVE LOGITS
    æĺİ天
    0.10
    åĴĮ个人
    0.09
    unks
    0.09
    awan
    0.09
    azar
    0.09
    andre
    0.09
    ForResource
    0.09
    zw
    0.08
    pta
    0.08
    ossil
    0.08
    Activations Density 0.028%

    No Known Activations