© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38505
    Prev
    Next
    INDEX
    Explanations

    keep in mind

    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
    æ§
    -0.10
    éĻ¤æѤ
    -0.10
    对ä¸įèµ·
    -0.09
    èĩªåľ¨
    -0.09
    åĭĭç«ł
    -0.09
    æ¡Ģ
    -0.09
    å¾Ĺèµ·
    -0.09
    é¸
    -0.09
    æĪĸå°Ĩ
    -0.09
    ospace
    -0.09
    POSITIVE LOGITS
    lessly
    0.09
    è¿Ļæĺ¯ä¸Ģ个
    0.09
    erman
    0.09
    mium
    0.08
    åıªå¾Ĺ
    0.08
    æĥ¦
    0.08
    çī¢è®°
    0.08
     mind
    0.08
    riage
    0.08
     Moder
    0.08
    Activations Density 0.008%

    No Known Activations