© 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. 35421
    Prev
    Next
    INDEX
    Explanations

    traffic congestion and jams

    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
     stages
    -0.09
    æıŃå¼Ģ
    -0.09
     steps
    -0.09
    ër
    -0.08
    æĴº
    -0.08
     stage
    -0.08
    çŃĸåĪĴ
    -0.08
     Py
    -0.08
     roller
    -0.08
    ounty
    -0.08
    POSITIVE LOGITS
    æĭ¥åłµ
    0.21
    åłµ
    0.18
     congestion
    0.16
    åłµå¡ŀ
    0.16
     tắc
    0.15
    æĭ¥æĮ¤
    0.15
    çĸıéĢļ
    0.15
    交éĢļ
    0.14
     traffic
    0.13
    è·¯åĨµ
    0.13
    Activations Density 0.211%

    No Known Activations