© 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. 34834
    Prev
    Next
    INDEX
    Explanations

    cemeteries or places

    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
    æ±Ģ
    -0.09
    æŦ
    -0.09
    asic
    -0.08
    尾巴
    -0.08
    éŃĤ
    -0.08
    é£İåı£
    -0.08
    æĬ¤èº«ç¬¦
    -0.08
    åĹĶ
    -0.08
    åħij
    -0.08
    ноÑģ
    -0.08
    POSITIVE LOGITS
    éĺ²èħIJ
    0.10
    naire
    0.10
    utherford
    0.09
    IGGER
    0.09
    åĸĦ
    0.09
    æ®Ħ
    0.09
    æ¯ıä¸Ģ天
    0.09
    åݲ
    0.09
    اÙģÙĬ
    0.08
    _STS
    0.08
    Activations Density 0.001%

    No Known Activations