© 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. 5329
    Prev
    Next
    INDEX
    Explanations

    modern human

    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
    平淡
    -0.10
    顺åºĶ
    -0.10
    PLIC
    -0.09
    å®£ä¼ł
    -0.09
    earned
    -0.09
    ä¸Ģå¿ĥ
    -0.09
    ecn
    -0.09
    æį¨
    -0.09
    èµĶ
    -0.09
    æķĻä½ł
    -0.09
    POSITIVE LOGITS
    inea
    0.09
    åĶ±æŃĮ
    0.09
    à¹Ģà¸ľ
    0.08
     race
    0.08
    sap
    0.08
    æ¨¡æł·
    0.08
    race
    0.08
    ises
    0.08
     Straw
    0.08
    als
    0.08
    Activations Density 0.040%

    No Known Activations