© 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. 47935
    Prev
    Next
    INDEX
    Explanations

    moving towards

    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
    åĪĩå®ŀ
    -0.10
    æ°IJ
    -0.10
    讲究
    -0.10
    yme
    -0.09
     OTHERWISE
    -0.09
    -standing
    -0.09
    oug
    -0.09
    纨
    -0.09
    æµģåĬ¨æĢ§
    -0.09
    为æ°ij
    -0.09
    POSITIVE LOGITS
    缮æłĩ
    0.12
     towards
    0.11
     toward
    0.11
    æī¹
    0.11
    çļĦæĸ¹åIJij
    0.11
    缮æ¨Ļ
    0.10
    marsh
    0.10
     Tow
    0.10
    çļĦ缮æłĩ
    0.10
    Towards
    0.09
    Activations Density 0.028%

    No Known Activations