© 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. 24258
    Prev
    Next
    INDEX
    Explanations

    explaining something

    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
    峡
    -0.10
    寡
    -0.09
    .truth
    -0.09
    åıĹçģ¾
    -0.09
    à¹Ħà¸Ĺ
    -0.09
    VRT
    -0.09
    æīĢèĩ´
    -0.09
    æ±°
    -0.09
    æī«ä¸Ģæī«
    -0.09
    xca
    -0.09
    POSITIVE LOGITS
    éŀŃ
    0.11
    alled
    0.09
    arie
    0.09
    _more
    0.09
    ä¹Łå°±
    0.08
    æĪij们å¿ħé¡»
    0.08
    æŀĦ
    0.08
    åıĭ
    0.08
    æįŁå®³
    0.08
    alls
    0.08
    Activations Density 0.011%

    No Known Activations