© 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. 11648
    Prev
    Next
    INDEX
    Explanations

    moments in 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
    aho
    -0.10
    è´¢åĬĽ
    -0.10
    æĹºçĽĽ
    -0.09
    æĢ§çĸ¾çĹħ
    -0.09
    ниÑĨÑĭ
    -0.09
    à¸ģะ
    -0.09
    edly
    -0.08
    å¾Ĵ
    -0.08
    _firstname
    -0.08
    ovah
    -0.08
    POSITIVE LOGITS
     moments
    0.22
     moment
    0.18
     Moments
    0.18
    éĤ£ä¸ĢåĪ»
    0.18
     моменÑĤ
    0.17
     Moment
    0.17
    æŶåĪ»
    0.16
    è¿Ļä¸ĢåĪ»
    0.16
    Moment
    0.16
    moment
    0.15
    Activations Density 0.052%

    No Known Activations