© 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. 4686
    Prev
    Next
    INDEX
    Explanations

    Convert back to string

    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
    åıĪä¸Ģ次
    -0.11
    çĤķ
    -0.10
    æł¹æľ¬å°±ä¸į
    -0.09
    æľ¬èº«çļĦ
    -0.09
    å¾Ī好çļĦ
    -0.09
    è¿Ļä¹Īåģļ
    -0.09
    èĭ¦èĭ¦
    -0.09
     itself
    -0.09
    æĹ©åľ¨
    -0.08
    æľ¬èº«å°±
    -0.08
    POSITIVE LOGITS
    çĦ¶åIJİ
    0.12
    orem
    0.10
    /Set
    0.10
    çĦ¶å¾Į
    0.10
    并å°Ĩ
    0.09
    Ñĭв
    0.09
    nez
    0.09
    then
    0.09
    egas
    0.09
     Bundy
    0.09
    Activations Density 0.030%

    No Known Activations