© 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. 54485
    Prev
    Next
    INDEX
    Explanations

    states of being and remaining parts

    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
    ä¼ļ让
    -0.13
    ä¼ļè®©ä½ł
    -0.12
    ä¼ļ导èĩ´
    -0.11
    åıĤåĬłäºĨ
    -0.11
    åı¯ä»¥è®©
    -0.10
    å½ĵä»ĸ
    -0.10
    çī¹æĿĥ
    -0.10
    åĬĽè¿ĺæĺ¯
    -0.10
    å°Ĩè¿Ľä¸ĢæŃ¥
    -0.10
    è°ģçŁ¥éģĵ
    -0.10
    POSITIVE LOGITS
     being
    0.26
    being
    0.21
     sendo
    0.17
     becoming
    0.15
    Being
    0.15
     Being
    0.15
     siendo
    0.13
     étant
    0.13
    -being
    0.11
    æľĿçĿĢ
    0.11
    Activations Density 0.319%

    No Known Activations