© 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. 62526
    Prev
    Next
    INDEX
    Explanations

    because/due to

    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
    inate
    -0.11
    าร
    -0.10
    aine
    -0.10
    inating
    -0.09
     addTarget
    -0.09
    ictim
    -0.09
    .addElement
    -0.09
    cth
    -0.09
    æĸŁ
    -0.09
    anness
    -0.09
    POSITIVE LOGITS
    èĩ»
    0.09
    çħ
    0.09
    edom
    0.08
    iah
    0.08
    ä¿¡æģ¯ç³»ç»Ł
    0.08
    çŀŃ
    0.08
    pile
    0.08
    è¿ŀè¿ŀ
    0.08
    lined
    0.08
    趣
    0.07
    Activations Density 0.077%

    No Known Activations