© 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. 9916
    Prev
    Next
    INDEX
    Explanations

    license or legal text

    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
    æīĢæıIJä¾ĽçļĦ
    -0.09
    çļĦ羣å®ŀ
    -0.08
    ç«£
    -0.08
    æĢĿ念
    -0.08
    æ¡Ķ
    -0.07
    åīįéĿ¢
    -0.07
    æī¾åĩĨ
    -0.07
    çİĩé¢Ĩ
    -0.07
    appers
    -0.07
    åĩºåİĤ
    -0.07
    POSITIVE LOGITS
    åįģæĿ¡
    0.12
    é¢ģå¸ĥ
    0.11
    è¿Ŀåıį
    0.11
     enforcement
    0.10
    è¿Ļå¥Ĺ
    0.10
    书éĿ¢
    0.10
     Enforcement
    0.10
    åħ¬å¸ĥ
    0.10
     enforce
    0.10
    éĢĤçĶ¨äºİ
    0.10
    Activations Density 0.250%

    No Known Activations