© 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. 10060
    Prev
    Next
    INDEX
    Explanations

    serial numbers mixed with 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
    IFA
    -0.09
    æĬ
    -0.08
    èĢ½
    -0.08
    代è¨Ģ
    -0.08
     Moff
    -0.08
    çĽ¸ä¿¡å¤§å®¶
    -0.08
    ç¼´è´¹
    -0.08
    åĪ¶åº¦æĶ¹éĿ©
    -0.07
     ASM
    -0.07
    .nb
    -0.07
    POSITIVE LOGITS
    è¾Ĺ
    0.09
    çĮ·
    0.09
    essim
    0.09
    ä¸į容
    0.08
    packed
    0.08
    å®°
    0.08
    worth
    0.08
    京津
    0.08
    tre
    0.08
    æľ¬æĬ¥
    0.08
    Activations Density 0.306%

    No Known Activations