© 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. 1040
    Prev
    Next
    INDEX
    Explanations

    glad you asked/called/have/be

    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
    åĨįä¸Ģ次
    -0.09
    æĹłä¸į
    -0.09
    çĮĹ
    -0.09
    èı±
    -0.09
    ullet
    -0.08
    æĽ´å¼º
    -0.08
    æĽ´æľī
    -0.08
    çŤ
    -0.08
    .PropertyType
    -0.08
     Bund
    -0.08
    POSITIVE LOGITS
    éĤ£è¾¹
    0.09
    å¦ĤæѤ
    0.09
     Crowd
    0.09
    è¿ŀäºij
    0.08
    éĤ£åĦ¿
    0.08
    åī¯
    0.08
     Gaz
    0.08
    çĻ½æ²Ļ
    0.08
     circum
    0.08
    éľĩæĴ¼
    0.08
    Activations Density 0.008%

    No Known Activations