© 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. 55091
    Prev
    Next
    INDEX
    Explanations

    php /** comment

    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
    ä¾Ľå¤§å®¶
    -0.08
    è¿ĺå¾Ĺ
    -0.08
    çŃĿ
    -0.08
    æĭįæĭį
    -0.08
    Browse
    -0.08
    çĶŃ
    -0.08
    é¹Ī
    -0.08
    roud
    -0.08
    ewise
    -0.08
    äºĨåIJĹ
    -0.08
    POSITIVE LOGITS
    intree
    0.09
    TING
    0.09
    yon
    0.09
    å¦Ĥä½ķ
    0.08
    ziaÅĤ
    0.08
    /how
    0.08
    illet
    0.08
    æĹ¢çĦ¶
    0.08
    eva
    0.08
    enk
    0.08
    Activations Density 0.047%

    No Known Activations