© 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. 61685
    Prev
    Next
    INDEX
    Explanations

    explaining what something is

    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
    æķij人
    -0.10
    åį°
    -0.09
    ivism
    -0.09
    nes
    -0.08
    è¶Ĭæĺ¯
    -0.08
     Watkins
    -0.08
    ibur
    -0.08
    astic
    -0.08
    arin
    -0.08
    екÑĤив
    -0.08
    POSITIVE LOGITS
    çŃĶæ¡Ī
    0.21
     answer
    0.20
    åĽŀçŃĶ
    0.20
    çļĦçŃĶæ¡Ī
    0.19
    è¿Ļ个éĹ®é¢ĺ
    0.18
    çŃĶãģĪ
    0.18
    çļĦåĽŀçŃĶ
    0.18
     answering
    0.16
    answer
    0.16
    	answer
    0.15
    Activations Density 0.218%

    No Known Activations