© 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. 1490
    Prev
    Next
    INDEX
    Explanations

    parliamentary matters and institutions

    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
    ç»Ħéķ¿
    -0.11
    ÑĥÑģÑĤ
    -0.10
    adic
    -0.09
    äºĭãģĮ
    -0.09
    æĪijçľĭ
    -0.09
    sing
    -0.09
    ider
    -0.08
     Incorporated
    -0.08
    úb
    -0.08
     nh
    -0.08
    POSITIVE LOGITS
    zell
    0.10
    ten
    0.10
    æŀķ
    0.10
    åĪ¶åº¦æĶ¹éĿ©
    0.09
    arians
    0.09
    time
    0.09
    ainment
    0.09
    á»į
    0.09
    rupt
    0.08
     sire
    0.08
    Activations Density 0.015%

    No Known Activations