© 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. 18346
    Prev
    Next
    INDEX
    Explanations

    people descriptions and attributes

    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
    åħ¼
    -0.08
    è¦ģåģļåĪ°
    -0.08
    å°½
    -0.08
    Ùħض
    -0.08
     Lodge
    -0.08
    ä¸ĸçķĮä¸Ģæµģ
    -0.08
    çªģåĩºéĹ®é¢ĺ
    -0.08
    æĦ¿
    -0.08
     lodging
    -0.08
    款
    -0.07
    POSITIVE LOGITS
    æݨçIJĨ
    0.12
    ascript
    0.10
    å®ŀä½ĵ
    0.09
    çĶŁæ´»åľ¨
    0.09
    åĽłæŀľ
    0.09
    æĴij
    0.09
    æ·Į
    0.09
    æĬ»
    0.08
    æĹłç¼ĺ
    0.08
    æĸĩåĮĸä¼łåªĴ
    0.08
    Activations Density 0.353%

    No Known Activations