© 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. 48156
    Prev
    Next
    INDEX
    Explanations

    use, modify, publish, distribute

    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
    è´¢åĬĽ
    -0.09
    DED
    -0.09
     ÙĪج
    -0.09
     presum
    -0.09
    æµĨ
    -0.09
    URA
    -0.08
    è¿Ļ个éĹ®é¢ĺ
    -0.08
    à¸Ĥà¸Ļ
    -0.08
    ä¸įè¦ģ太
    -0.08
    -Za
    -0.08
    POSITIVE LOGITS
    ’h
    0.08
    èĹī
    0.08
    .itemView
    0.08
    ä¿Ĺ
    0.08
    resse
    0.08
    åĨ»
    0.08
    æ»ŀ
    0.08
    伪è£ħ
    0.08
     sag
    0.08
     ‘
    0.07
    Activations Density 0.051%

    No Known Activations