© 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. 58252
    Prev
    Next
    INDEX
    Explanations

    the other, the rest, the like

    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
    ziel
    -0.09
    æĥ´
    -0.09
     bos
    -0.09
    .Suppress
    -0.09
    amic
    -0.09
    ield
    -0.09
    御
    -0.09
    å®Įåħ¨æ²¡æľī
    -0.09
    æľīè¿Ļæł·çļĦ
    -0.09
    ä¸Ģåı·
    -0.09
    POSITIVE LOGITS
    åħ¶ä½Ļ
    0.22
    åī©ä¸ĭçļĦ
    0.15
     others
    0.15
     rest
    0.14
     remaining
    0.14
    åī©ä½Ļ
    0.13
     resto
    0.13
    others
    0.13
    åī©ä¸ĭ
    0.13
     reste
    0.12
    Activations Density 0.071%

    No Known Activations