© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34431
    Prev
    Next
    INDEX
    Explanations

    agenda

    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
    Not in Any Lists

    No Comments

    Negative Logits
    jack
    -0.09
    éļĶ
    -0.09
     tre
    -0.09
    ulan
    -0.09
    éģĭçĶ¨
    -0.09
    æĺ¥è¿IJ
    -0.08
    åŨ
    -0.08
    åħį
    -0.08
    å²Ĺ
    -0.08
    è¿IJçĶ¨
    -0.08
    POSITIVE LOGITS
     agenda
    0.18
    agenda
    0.17
     agendas
    0.15
    è®®é¢ĺ
    0.15
     Agenda
    0.15
    è®®
    0.12
    è®®äºĭ
    0.11
    åľŃ
    0.09
    èŃ°
    0.09
    çĿĢæĢ¥
    0.09
    Activations Density 0.029%

    No Known Activations