© 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. 5173
    Prev
    Next
    INDEX
    Explanations

    for any purpose

    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
    对åħ¬åı¸
    -0.09
    对ä¼ģä¸ļ
    -0.08
    产æĿĥ
    -0.08
    æĤ¬å´ĸ
    -0.08
    çİ°æľī
    -0.08
     rant
    -0.08
    çĶ¸
    -0.08
    åģļå¾Ĺ
    -0.08
    ianne
    -0.08
    æĵİ
    -0.08
    POSITIVE LOGITS
    缮çļĦ
    0.20
     purposes
    0.19
    çĶ¨éĢĶ
    0.17
     purpose
    0.15
    çļĦ缮çļĦ
    0.15
    Purpose
    0.12
    purpose
    0.12
     목ìłģ
    0.12
     Purpose
    0.11
     PURPOSE
    0.11
    Activations Density 0.053%

    No Known Activations