© 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. 32793
    Prev
    Next
    INDEX
    Explanations

    dietary consumption and guidance

    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
    ä¸į容
    -0.09
    åºĶä»ĺ
    -0.08
    缴è¨Ģ
    -0.08
     fest
    -0.08
     BN
    -0.08
    æIJ
    -0.07
     Theatre
    -0.07
    æĬĺåıł
    -0.07
     ec
    -0.07
    KER
    -0.07
    POSITIVE LOGITS
    æ¶Īè´¹
    0.11
    èĨ³é£Ł
    0.11
    æĻ®åıĬ
    0.11
    æ¶Īè²»
    0.10
    æĵIJ
    0.10
     dietary
    0.10
    第äºĮ大
    0.10
     Shields
    0.10
    å¤§åĽ½
    0.10
    é»į
    0.10
    Activations Density 0.096%

    No Known Activations