© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52709
    Prev
    Next
    INDEX
    Explanations

    affairs division, bureau, council, minister, office

    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
    ı
    -0.10
    çĶŁæ´»çݯå¢ĥ
    -0.09
    Ń
    -0.09
    keit
    -0.09
    çİĩè¾¾åĪ°
    -0.09
    ãĥ¼ãĤ¿ãĥ¼
    -0.08
    º
    -0.08
    TER
    -0.08
    ä¼ŀ
    -0.08
    没æĥ³åĪ°
    -0.08
    POSITIVE LOGITS
    uate
    0.11
    ivals
    0.11
    ships
    0.10
    ä»ĬçĶŁ
    0.10
    usters
    0.10
    teen
    0.10
    angement
    0.10
     дела
    0.09
    ment
    0.09
    ä¹İ
    0.09
    Activations Density 0.009%

    No Known Activations