© 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. 57771
    Prev
    Next
    INDEX
    Explanations

    personal possessions or descriptions

    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
    à¹Ģà¸Ħย
    -0.10
    aub
    -0.09
    æľªæĪIJ
    -0.09
     Vor
    -0.08
    çĴľ
    -0.08
    è½¹
    -0.08
    éĥĿ
    -0.08
    æ¶Ī
    -0.08
    ä»Ģä¹ĪæŶåĢĻ
    -0.08
    éģĩéļ¾
    -0.08
    POSITIVE LOGITS
    å¤ļä½Ļ
    0.09
    á»ĩ
    0.09
    bil
    0.09
    adow
    0.09
    åĴı
    0.09
    æĺ§
    0.08
    ä½İåİĭ
    0.08
    ä¼Ĺ
    0.08
    åºĦ
    0.08
    AdapterFactory
    0.08
    Activations Density 0.017%

    No Known Activations