© 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. 11430
    Prev
    Next
    INDEX
    Explanations

    concerned with or involved in

    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
    é¦Ī
    -0.08
    çijŁ
    -0.08
    æĢ»ä¹¦è®°
    -0.08
    è¦ģçľĭ
    -0.08
    åĪ¶åº¦
    -0.08
    太å°ij
    -0.08
    æĪĺäºī
    -0.08
    ftype
    -0.08
    oru
    -0.07
    o
    -0.07
    POSITIVE LOGITS
     involvement
    0.15
    åıĤä¸İåĪ°
    0.15
    åıĤä¸İ
    0.14
     involved
    0.14
    æ²īæµ¸åľ¨
    0.13
    æ¶īåıĬåĪ°
    0.12
    åıĥèĪĩ
    0.12
    éĸ¢ãĤı
    0.10
    ä¸ĵ注äºİ
    0.10
    æĬķåħ¥åĪ°
    0.10
    Activations Density 0.119%

    No Known Activations