© 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. 38688
    Prev
    Next
    INDEX
    Explanations

    side of things or doing business

    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
    åį³æŶ
    -0.09
    ennie
    -0.08
    满èĦ¸
    -0.08
    $output
    -0.08
    飽
    -0.08
    åŀ¢
    -0.08
    éľİ
    -0.08
    ذر
    -0.08
    çĻ»
    -0.08
    åĩĨ
    -0.08
    POSITIVE LOGITS
     things
    0.23
    things
    0.19
    äºĭçī©
    0.18
    äºĭæĥħ
    0.18
     Things
    0.16
     thing
    0.16
    ä¸ľè¥¿
    0.16
    Things
    0.15
    äºĭåĦ¿
    0.15
    ä¸ĢåĪĩ
    0.15
    Activations Density 0.076%

    No Known Activations