© 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. 809
    Prev
    Next
    INDEX
    Explanations

    Faulkner, Nixon, cauliflower, Maulvi

    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
    ãģĹãĤĩãģĨ
    -0.10
    azon
    -0.10
    olon
    -0.10
    /rec
    -0.10
    çĸ²åĬ³
    -0.10
    ä¿ĺ
    -0.10
    ë£Į
    -0.10
    çŁ¿çī©
    -0.10
    arnation
    -0.10
    ิà¸ģ
    -0.10
    POSITIVE LOGITS
    er
    0.09
    Ñĩик
    0.09
    fer
    0.08
    mente
    0.08
    urally
    0.08
    åĪģ
    0.08
    ier
    0.08
    ous
    0.08
    tri
    0.08
    ../../../
    0.08
    Activations Density 0.001%

    No Known Activations