© 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. 3470
    Prev
    Next
    INDEX
    Explanations

    knowing context or information

    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
     اÙĦØ£Ùħر
    -0.10
    oose
    -0.10
    -dat
    -0.10
    æĪijçĽ¸ä¿¡
    -0.10
    eer
    -0.09
    arness
    -0.09
    å¹ħ
    -0.09
    ió
    -0.09
    bone
    -0.08
    åIJįåı«
    -0.08
    POSITIVE LOGITS
    ledged
    0.14
    lege
    0.10
    åIJĪãģĦ
    0.10
    ingly
    0.10
    äºĽä»Ģä¹Ī
    0.10
    fully
    0.09
    å¦Ĥä½ķåİ»
    0.09
    vation
    0.09
    sand
    0.09
    ledge
    0.09
    Activations Density 0.110%

    No Known Activations