© 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. 1163
    Prev
    Next
    INDEX
    Explanations

    most [noun]

    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
    åįģ足
    -0.11
    æŁIJäºĽ
    -0.10
    bart
    -0.10
    ä¸Ģå®ļç¨ĭ度
    -0.09
    asan
    -0.09
    ismo
    -0.09
     Certain
    -0.09
    mere
    -0.09
    ä¸ĩä¸Ģ
    -0.09
    è¯ħ
    -0.09
    POSITIVE LOGITS
    /all
    0.16
    æĥħåĨµä¸ĭ
    0.14
     importantly
    0.13
    sWith
    0.12
    place
    0.12
    eller
    0.11
    è¿ĺæĺ¯è¦ģ
    0.11
    owing
    0.10
    人çļĦ
    0.10
    oj
    0.10
    Activations Density 0.036%

    No Known Activations