© 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. 34724
    Prev
    Next
    INDEX
    Explanations

    I pronouns

    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
    éĿŀ常å¤ļçļĦ
    -0.11
    åıĪæľī
    -0.11
    åħ¶å®ŀ
    -0.10
    åħ¶å®ŀæĺ¯
    -0.10
    èĺijèıĩ
    -0.10
    /or
    -0.10
    好åĥı
    -0.10
    æį®è¯´
    -0.09
    èıĩ
    -0.09
    ëį°
    -0.09
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.14
     ever
    0.14
     EVER
    0.12
    羣æĺ¯
    0.12
     anything
    0.10
    æĥ³è¦ģ
    0.10
    åĨįå¤ļ
    0.10
     gerçekten
    0.10
    anything
    0.10
    è¿Ļæł·çļĦè¯Ŀ
    0.10
    Activations Density 0.163%

    No Known Activations