© 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. 26815
    Prev
    Next
    INDEX
    Explanations

    "I" followed by uncertainty or queries

    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
     flash
    -0.09
    Smooth
    -0.09
    áºŃn
    -0.08
    åıªè¦ģä½ł
    -0.08
    posable
    -0.08
     Ton
    -0.08
    flash
    -0.08
    éĺ¶æ¢¯
    -0.08
    人èĦī
    -0.08
    Ton
    -0.08
    POSITIVE LOGITS
    .SDK
    0.10
    ãģĹãģŁãĤĤãģ®
    0.09
    à¹Ħ
    0.09
    æħ·
    0.09
    ãĥĬ
    0.09
    讲述äºĨ
    0.09
    à¸Īำà¸ģ
    0.09
    æľªèĥ½
    0.09
    /Branch
    0.09
    èµIJ
    0.09
    Activations Density 0.013%

    No Known Activations