© 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. 23928
    Prev
    Next
    INDEX
    Explanations

    rising star

    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
    æīĵåĩ»
    -0.09
    工夫
    -0.09
    æĭĸ延
    -0.09
    æĥħ人èĬĤ
    -0.09
    触
    -0.08
    å±ħ
    -0.08
    iface
    -0.08
    è©Ī
    -0.08
    æŃ£çīĪ
    -0.08
    é¾Ľ
    -0.08
    POSITIVE LOGITS
    å´Ľèµ·
    0.18
    å´Ń
    0.14
    åĬ¿å¤´
    0.13
    èĦ±é¢ĸèĢĮåĩº
    0.13
    rise
    0.12
    æ½ľåĬĽ
    0.12
    åīįéĢĶ
    0.12
    åłª
    0.12
    å¹´è½»
    0.12
     rising
    0.11
    Activations Density 0.088%

    No Known Activations