© 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. 58873
    Prev
    Next
    INDEX
    Explanations

    any

    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
    è¶Ĭå¤ļ
    -0.09
    æľĭåıĭ们
    -0.08
    stdafx
    -0.08
    娩
    -0.08
    Ø´ÙĨ
    -0.08
     different
    -0.08
    çĶ¨èį¯
    -0.08
     very
    -0.08
    å®ģ
    -0.08
    ä½łä»¥ä¸º
    -0.08
    POSITIVE LOGITS
    å¹´é¾Ħ段
    0.11
    çĬ¶æĢģä¸ĭ
    0.10
    -sized
    0.10
    èĩªçĦ¶èĢĮ
    0.10
    oi
    0.09
    åıªè¦ģæĺ¯
    0.09
    åģ¥åº·çļĦ
    0.09
    ç±»åŀĭçļĦ
    0.09
    被æĬĵ
    0.09
    eer
    0.09
    Activations Density 0.040%

    No Known Activations