© 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. 30263
    Prev
    Next
    INDEX
    Explanations

    watching and observing

    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
    æĶ¶åĪ°
    -0.09
    ç´Ĭä¹±
    -0.09
    æĮ¤
    -0.09
    éĽī
    -0.08
    åIJĪä¼Ļ人
    -0.08
    å®ĮæĪIJäºĨ
    -0.08
    GRES
    -0.08
    è¿ĩçļĦ
    -0.08
    亡
    -0.08
    licing
    -0.08
    POSITIVE LOGITS
    çĽijæµĭ
    0.24
    çĽijæݧ
    0.24
    çĽijè§Ĩ
    0.23
    å¯ĨåĪĩåħ³æ³¨
    0.21
     monitoring
    0.20
     monitor
    0.20
    monitor
    0.19
    Monitor
    0.18
     Monitoring
    0.18
    .monitor
    0.17
    Activations Density 0.126%

    No Known Activations