© 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. 11676
    Prev
    Next
    INDEX
    Explanations

    circumstances and environment changes

    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
    æģ¯æģ¯
    -0.10
    飧æĢ§
    -0.10
    venture
    -0.10
     ÑĢоман
    -0.09
    ared
    -0.09
    éĤĢ
    -0.09
    äºĨæĪijçļĦ
    -0.09
    geme
    -0.09
    ä¸įåĩº
    -0.09
    /XMLSchema
    -0.09
    POSITIVE LOGITS
    å®ŀéĻħæĥħåĨµ
    0.17
    åħ·ä½ĵæĥħåĨµ
    0.14
     circumstances
    0.12
    å¸ĤåľºéľĢæ±Ĥ
    0.12
    æĥħåĨµ
    0.12
    éľĢæ±Ĥ
    0.11
    å±ĢåĬ¿
    0.11
    å¤ĸçķĮ
    0.11
    å¤ĸéĥ¨
    0.11
     needs
    0.11
    Activations Density 0.127%

    No Known Activations