© 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. 61610
    Prev
    Next
    INDEX
    Explanations

    time for or time to

    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
    åı¯çĶ¨äºİ
    -0.10
    æĽ´è¦ģ
    -0.09
    wi
    -0.09
     Grades
    -0.08
    æݾ
    -0.08
    è¦ģç´§
    -0.08
    èŀŁ
    -0.08
    aways
    -0.08
    presso
    -0.08
    åĩĢåľŁ
    -0.08
    POSITIVE LOGITS
    æīĢæľī人éĥ½
    0.09
    æīĢæľī人
    0.09
    elong
    0.09
    .hasOwnProperty
    0.09
    æĢ§çļĦ
    0.08
    ÑĢин
    0.08
    fully
    0.08
    lessly
    0.08
    ephir
    0.08
    éĩĬæĶ¾
    0.08
    Activations Density 0.005%

    No Known Activations