© 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. 63543
    Prev
    Next
    INDEX
    Explanations

    fitbit, healthkit, connect

    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
    å¿ĥæĻº
    -0.10
    éľŃ
    -0.09
    åĪĨæķ°çº¿
    -0.09
    è¿ŁåĪ°
    -0.09
     Pub
    -0.09
     homophobic
    -0.09
    .Inject
    -0.08
    é¥ķ
    -0.08
    æīĵæŀ¶
    -0.08
    å¼Ģåľº
    -0.08
    POSITIVE LOGITS
    éĽĢ
    0.10
    åģ¥èº«
    0.10
    èĬ½
    0.09
     ÑĦин
    0.09
    æ´¼
    0.09
    çĶµéĩı
    0.09
    éĵ§
    0.09
    å¾ĭ
    0.09
    æīĵåį¡
    0.09
    aza
    0.09
    Activations Density 0.065%

    No Known Activations