© 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. 48633
    Prev
    Next
    INDEX
    Explanations

    discoveries and anticipation

    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
    æīįçŁ¥éģĵ
    -0.10
    æ¡ĥ
    -0.10
    çľĭåĪ°äºĨ
    -0.09
    å¦Ĥä½ķçľĭå¾ħ
    -0.09
    è¦ģçľĭ
    -0.09
    å¾ĹçŁ¥
    -0.09
    çľĭåĪ°
    -0.08
    zed
    -0.08
    æ£ł
    -0.08
    çľ·
    -0.08
    POSITIVE LOGITS
    说åĩºæĿ¥
    0.12
    为大家
    0.12
    eric
    0.12
    å±ķ示
    0.12
    ä¼łè¾¾
    0.11
    ç»Ļ大家
    0.11
    为广大
    0.11
    çĪĨåĩº
    0.11
    å°±ç»Ļ大家
    0.11
    带ç»Ļ
    0.11
    Activations Density 0.422%

    No Known Activations