© 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. 7287
    Prev
    Next
    INDEX
    Explanations

    While/Although clauses

    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
    ä¸įåħ·å¤ĩ
    -0.10
    APPED
    -0.09
     Verb
    -0.09
    amma
    -0.09
    çļĦåľ°ä½į
    -0.09
    athed
    -0.08
    ÙĩÙħا
    -0.08
    ÑĤиÑĢ
    -0.08
    gie
    -0.08
     Prism
    -0.08
    POSITIVE LOGITS
    å¾Īæĥ³
    0.10
    .NotNull
    0.09
    ä¹Łå¸ĮæľĽ
    0.09
    çĪ±ç¾İ
    0.09
    带åĪ°
    0.09
    å¾Īé«ĺåħ´
    0.09
    icker
    0.09
    ä¹Łæĺ¯å¾Ī
    0.09
    éĹªåħī
    0.08
    áºŃn
    0.08
    Activations Density 0.052%

    No Known Activations