© 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. 26139
    Prev
    Next
    INDEX
    Explanations

    optical fiber and cables

    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
    æ·Ģ
    -0.09
    渤
    -0.09
    ATO
    -0.09
    atori
    -0.09
    åıĹ害人
    -0.09
    _published
    -0.08
    åŀ£
    -0.08
     ÑĦоÑĢ
    -0.08
     pint
    -0.08
    ultipart
    -0.08
    POSITIVE LOGITS
    åħī纤
    0.12
    èĮ¶åĽŃ
    0.10
     cement
    0.10
    омеÑĢ
    0.10
     Cement
    0.10
    干线
    0.10
    éļıæŶéļıåľ°
    0.09
    iance
    0.09
    tro
    0.09
    涵
    0.09
    Activations Density 0.153%

    No Known Activations