© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51621
    Prev
    Next
    INDEX
    Explanations

    Elizabeth followed by names

    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
    ìį¨
    -0.11
    itus
    -0.10
    ä¸įäºĨ
    -0.10
    ä½ĵè´´
    -0.10
    igan
    -0.10
    arem
    -0.09
    åŁİéĻħ
    -0.09
    ilogy
    -0.09
    ITION
    -0.09
    é©¿
    -0.09
    POSITIVE LOGITS
     Ñģобой
    0.12
    anne
    0.11
    mate
    0.11
    anes
    0.10
    sam
    0.09
    ably
    0.09
    ams
    0.09
    rary
    0.09
    æ³Ľ
    0.09
    ais
    0.09
    Activations Density 0.026%

    No Known Activations