© 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. 52969
    Prev
    Next
    INDEX
    Explanations

    until now

    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
    çıŃ
    -0.10
    æĭľ
    -0.10
    Ùħرة
    -0.09
    æ½¢
    -0.09
    former
    -0.09
    ugin
    -0.09
    çĽ²
    -0.09
    æĭĤ
    -0.09
    å¾Įä¾Ĩ
    -0.09
    æĤĴ
    -0.09
    POSITIVE LOGITS
    为æŃ¢
    0.12
    ä¸ĢçĽ´åľ¨
    0.10
    ä¸Ģ缴éĥ½
    0.09
    åĨįåĪ°
    0.09
    ìłĢ
    0.09
    åīįæīĢ
    0.08
    ienie
    0.08
    æѤåĪ»
    0.08
    aled
    0.08
    ä¸įæĦ¿
    0.08
    Activations Density 0.016%

    No Known Activations