© 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. 60634
    Prev
    Next
    INDEX
    Explanations

    too

    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
    æľīåĪ©
    -0.12
    æľīåĪ©äºİ
    -0.10
    otron
    -0.10
    aylor
    -0.10
    maal
    -0.09
    favor
    -0.09
    SKU
    -0.09
    éĤ»éĩĮ
    -0.09
    巨大
    -0.09
    èĦ¸éĥ¨
    -0.09
    POSITIVE LOGITS
     Maher
    0.10
    è¡Įä¸ļåıijå±ķ
    0.09
     recip
    0.09
    åĽłåľ°åĪ¶å®ľ
    0.09
    èĭ¹
    0.08
    èģĮæĿĥ
    0.08
    isel
    0.08
    onne
    0.08
    meric
    0.08
    Mah
    0.08
    Activations Density 0.021%

    No Known Activations