© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50460
    Prev
    Next
    INDEX
    Explanations

    network and gnome settings

    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
    ç«
    -0.12
    åı®
    -0.10
    omba
    -0.10
    åıĸåĩº
    -0.09
     Bj
    -0.09
    ç¦ıçī¹
    -0.09
    åĪĨå¸ĥ
    -0.09
    æł©
    -0.09
    çªĥ
    -0.08
    illard
    -0.08
    POSITIVE LOGITS
    å®ŀçĶ¨
    0.10
    ãĤ¸ãĥ£ãĥ³
    0.08
    ä¾Ŀèµĸ
    0.08
     ìĦ¤ìłķ
    0.08
    å¸ĤåľºåĮĸ
    0.08
    é«ĺæĺĤ
    0.08
    عÙĬ
    0.08
    Setting
    0.08
    _setting
    0.08
    -setting
    0.08
    Activations Density 0.146%

    No Known Activations