© 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. 48222
    Prev
    Next
    INDEX
    Explanations

    JBoss, WebLogic, WAS

    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
    侬
    -0.10
    绸
    -0.09
     Hardcore
    -0.09
    çļĩ
    -0.08
    åĽ½æĥħ
    -0.08
    LOC
    -0.08
    é¸Ń
    -0.08
    人社
    -0.08
    emm
    -0.08
    à¤ł
    -0.08
    POSITIVE LOGITS
     canadian
    0.10
    éĩijéĵ¶
    0.09
    :NS
    0.09
    æ¹į
    0.09
    éĩijéĻµ
    0.08
    åĵij
    0.08
    strike
    0.08
    颧
    0.08
    idor
    0.08
    寡
    0.08
    Activations Density 0.040%

    No Known Activations