© 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. 34495
    Prev
    Next
    INDEX
    Explanations

    login or register

    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
    ä¸įæĸŃæıIJé«ĺ
    -0.08
    ãĤĭãĤĤãģ®
    -0.08
    æĶ¾è¿Ľ
    -0.08
     Hudson
    -0.08
    çĸ«
    -0.08
    åįķ车
    -0.08
    é«ĺå°ļ
    -0.08
    çĪ±åĽ½
    -0.08
    sg
    -0.07
     proj
    -0.07
    POSITIVE LOGITS
    ä¸ĢåĪĩéĥ½æĺ¯
    0.10
    UPI
    0.10
     Bris
    0.09
     Gros
    0.09
    ancel
    0.09
    éķ¬
    0.09
    ãĥĪãĥ©
    0.09
    ìľĪ
    0.09
    åĸŁ
    0.09
    çĨ¹
    0.09
    Activations Density 0.017%

    No Known Activations