© 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. 22093
    Prev
    Next
    INDEX
    Explanations

    free Wi-Fi, parking, samples, or included amenities

    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
    ÑĮÑı
    -0.11
    èĦ¾æ°Ķ
    -0.10
     Giz
    -0.10
    bit
    -0.10
    侵害
    -0.09
    grass
    -0.09
    çįł
    -0.08
    gnu
    -0.08
    à¹ģà¸Ļะà¸Ļำ
    -0.08
    lice
    -0.08
    POSITIVE LOGITS
    zes
    0.09
    对人ä½ĵ
    0.09
    æ³Ĭ
    0.08
    zers
    0.08
     dou
    0.08
    å¾Ģè¿Ķ
    0.08
    -sw
    0.08
    ehr
    0.08
    åľ¨å¤ĸ
    0.08
    åħħ足çļĦ
    0.08
    Activations Density 0.005%

    No Known Activations