© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 595
    Prev
    Next
    INDEX
    Explanations

    storage units and transport

    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
    Negative Logits
    è¡Ģ液
    -0.09
    çĭŀ
    -0.09
    èįij
    -0.09
    bic
    -0.08
     rect
    -0.08
    轸
    -0.08
    ç¬Ķ
    -0.08
    çĥĽ
    -0.08
     butter
    -0.08
    èĦĨå¼±
    -0.08
    POSITIVE LOGITS
    ä»ĵ
    0.12
    åŀĽ
    0.11
    èĭ«
    0.10
    穹
    0.10
    åłĨæĶ¾
    0.10
    ä»ĵä½į
    0.09
    åħ¥åľº
    0.09
    åIJĥè¿ĩ
    0.09
    ri
    0.09
    fos
    0.09
    Activations Density 0.113%

    No Known Activations