© 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. 30028
    Prev
    Next
    INDEX
    Explanations

    ancient regions and history

    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
    éĶ¦ç»£
    -0.13
    åĬ¿
    -0.10
    åīįçŀ»
    -0.09
    åģ¥åº·æĪIJéķ¿
    -0.09
    AMS
    -0.09
    iction
    -0.09
    redd
    -0.09
    abet
    -0.08
    çģ«è½¦
    -0.08
    è£Ļ
    -0.08
    POSITIVE LOGITS
    eer
    0.10
    åħ®
    0.10
    кÑĢаÑĤ
    0.08
     TSRMLS
    0.08
    ÑģÑĤеÑĢ
    0.08
    ãģ¶ãĤĬ
    0.08
    бÑĥд
    0.08
     lan
    0.08
    otech
    0.08
    eking
    0.08
    Activations Density 0.009%

    No Known Activations