© 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. 57228
    Prev
    Next
    INDEX
    Explanations

    agricultural concepts and applications

    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
    èijŃ
    -0.09
    å·½
    -0.09
    åĬ¾
    -0.09
    ry
    -0.09
    tlement
    -0.09
    ness
    -0.09
    год
    -0.09
    å°ı康
    -0.09
    åµĺ
    -0.09
    缶
    -0.09
    POSITIVE LOGITS
    .assertj
    0.10
    å·¥ä½ľèĢħ
    0.10
    çĶ¨åĵģ
    0.10
    urally
    0.10
    ally
    0.09
    夫
    0.09
    ady
    0.09
    ë¦Ħ
    0.08
    çĶ¨è½¦
    0.08
    ä¸Ńåħ³æĿij
    0.08
    Activations Density 0.015%

    No Known Activations