© 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. 22654
    Prev
    Next
    INDEX
    Explanations

    appeals court

    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
    建档
    -0.10
    åħ¨æł¡
    -0.10
    onta
    -0.09
    æĹ¥äº§
    -0.09
    鸱
    -0.09
    erval
    -0.09
    管çIJĨåĪ¶åº¦
    -0.08
     вод
    -0.08
    åŃº
    -0.08
    åĩłå¼ł
    -0.08
    POSITIVE LOGITS
    DRV
    0.09
    åIJ¹
    0.09
    çŃīå¾ħ
    0.09
    çĸ®
    0.09
    asant
    0.09
    èħ°éĥ¨
    0.09
    æ´»å¾Ĺ
    0.08
    è§Ĵ度
    0.08
     blow
    0.08
     blown
    0.08
    Activations Density 0.668%

    No Known Activations