© 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. 5285
    Prev
    Next
    INDEX
    Explanations

    who or whom

    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
    çĸµ
    -0.09
    èĢģçĻ¾å§ĵ
    -0.09
    ilos
    -0.09
    жение
    -0.08
    ENU
    -0.08
    åŃ³
    -0.08
    çĶŁæľº
    -0.08
    æŀ¶
    -0.08
    è¡Ģèħ¥
    -0.08
    istas
    -0.08
    POSITIVE LOGITS
     whom
    0.14
    åIJįåŃĹ
    0.13
    å§ĵåIJį
    0.13
     who
    0.11
    æĺ¯è°ģ
    0.10
    æĺ¯ä»ĸ
    0.10
    以åıĬåħ¶ä»ĸ
    0.10
    èĤ¤èī²
    0.10
    è¿Ļ个åIJįåŃĹ
    0.09
    åĩłä¸ªäºº
    0.09
    Activations Density 0.124%

    No Known Activations