© 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. 18837
    Prev
    Next
    INDEX
    Explanations

    duration of time

    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
    ä¸Ģ个æľĪ
    -0.10
    ITT
    -0.10
    ä¸ī个æľĪ
    -0.10
    ä¸Ģæīĭ
    -0.09
    erton
    -0.09
    è°Ł
    -0.09
     меÑģÑıÑĨ
    -0.09
    èĩªå¸¦
    -0.09
     McD
    -0.09
     Month
    -0.09
    POSITIVE LOGITS
    çĻ¾å¹´
    0.17
    åįĥå¹´
    0.16
     centuries
    0.16
    åĩłåįģå¹´
    0.12
    ä¸ĸ代
    0.12
     century
    0.12
    åŃIJåŃĻ
    0.11
     decades
    0.11
    å¹´éĻIJ
    0.11
    -century
    0.11
    Activations Density 0.077%

    No Known Activations