© 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. 37027
    Prev
    Next
    INDEX
    Explanations

    going wrong

    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
    ä¸įæĺĵ
    -0.10
    itol
    -0.09
    éĤĪ
    -0.09
     crem
    -0.09
    è¿ĩçļĦ
    -0.09
    posium
    -0.09
    æį¢åıĸ
    -0.08
    oise
    -0.08
    AIN
    -0.08
    LEC
    -0.08
    POSITIVE LOGITS
    ä½ķåĨµ
    0.09
    æĺĻ
    0.09
     вÑĭбоÑĢ
    0.08
    æĸ¹ä½į
    0.08
    aska
    0.08
     Jam
    0.08
    æľīä»»ä½ķ
    0.08
    童年
    0.08
    éĢīæĭ©
    0.08
    ola
    0.07
    Activations Density 0.001%

    No Known Activations