© 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. 50000
    Prev
    Next
    INDEX
    Explanations

    mining ore geology minerals

    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
    unes
    -0.09
    åł°
    -0.09
    éĴ±å¸ģ
    -0.09
    .meta
    -0.09
    沸
    -0.09
    å·²å®ĮæĪIJ
    -0.08
     Coll
    -0.08
    åıijæİĺ
    -0.08
     coin
    -0.08
    æĮĸæİĺ
    -0.08
    POSITIVE LOGITS
     пÑĢим
    0.11
    涵
    0.10
    æ³¼
    0.10
    æľīä¿¡å¿ĥ
    0.10
    饶
    0.09
    baugh
    0.09
    itant
    0.09
    .truth
    0.08
     lic
    0.08
    /LICENSE
    0.08
    Activations Density 0.062%

    No Known Activations