© 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. 24049
    Prev
    Next
    INDEX
    Explanations

    response

    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
     Lorem
    -0.12
    çŃīåĨħ容
    -0.11
    çŃīçĹĩçĬ¶
    -0.10
     blah
    -0.10
    \\.
    -0.09
     allegedly
    -0.09
     ÑĤам
    -0.09
    Lorem
    -0.09
    éĹ®é¢ĺæĺ¯
    -0.09
    \u
    -0.09
    POSITIVE LOGITS
    æĬĬè¿Ļ个
    0.11
    æĬĬè¿ĻäºĽ
    0.10
    ",__
    0.10
    对æѤ
    0.10
    icter
    0.09
    dÅĤug
    0.08
    anke
    0.08
    prowadzi
    0.08
    indsight
    0.08
    à¹Ĥà¸Ľà¸£à¹ģ
    0.08
    Activations Density 17.462%

    No Known Activations