© 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. 21864
    Prev
    Next
    INDEX
    Explanations

    Los Angeles

    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
    å¾Ģä¸ĭ
    -0.10
    æĶ¾åѦ
    -0.09
    èij¬
    -0.09
    æ½ı
    -0.08
    交æİ¥
    -0.08
    ANDLE
    -0.08
     Schro
    -0.08
    å¾Ģå¤ĸ
    -0.08
    æł¼å¼ı
    -0.08
    овое
    -0.07
    POSITIVE LOGITS
    å±ķä½į
    0.19
    å±ķåĮº
    0.15
    å±ķåĩº
    0.14
    æ¼Ķ示
    0.14
     booth
    0.14
    äº®çĽ¸
    0.13
    å±ķ示
    0.13
    å±ķåĵģ
    0.13
    åıĤå±ķ
    0.12
    å±ķåİħ
    0.12
    Activations Density 0.102%

    No Known Activations