© 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. 11589
    Prev
    Next
    INDEX
    Explanations

    following "different"

    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
    inha
    -0.09
    idon
    -0.09
    çĤ¹æ»´
    -0.09
    ijing
    -0.08
    象
    -0.08
    ç®Ģ缴æĺ¯
    -0.08
    åįģéĩĮ
    -0.08
    广éĺĶçļĦ
    -0.08
    IDD
    -0.08
    tre
    -0.08
    POSITIVE LOGITS
    iable
    0.10
    leen
    0.08
    alls
    0.08
    姣
    0.08
    æªĢ
    0.08
     ali
    0.08
    ëį°
    0.08
    çĸ¼
    0.08
    amber
    0.08
    ej
    0.08
    Activations Density 0.033%

    No Known Activations