© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19527
    Prev
    Next
    INDEX
    Explanations

    quantities and amounts

    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
    6
    -0.09
    ãģªãĤĬ
    -0.08
    abet
    -0.08
    æĹ¢æĺ¯
    -0.08
     hung
    -0.08
    7
    -0.08
    为åĩĨ
    -0.08
    çĻ¾åĪĨä¹ĭ
    -0.07
    çĨ
    -0.07
    8
    -0.07
    POSITIVE LOGITS
    åħħåĪĨä½ĵçİ°
    0.10
    绸
    0.10
    æľĢåħ³éĶ®çļĦ
    0.10
     corresponding
    0.09
    è¿ĺæľīä¸ĢäºĽ
    0.09
    tas
    0.09
    å°±ä¸įèĥ½
    0.09
    çĭ¬
    0.09
    .PIPE
    0.09
    èĩ³æĸ¼
    0.09
    Activations Density 0.155%

    No Known Activations