© 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. 11504
    Prev
    Next
    INDEX
    Explanations

    depends on

    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
    Hier
    -0.08
    ael
    -0.08
    Microsoft
    -0.08
    mail
    -0.08
    _hierarchy
    -0.08
    ä¼Ĺ人
    -0.07
    åħĦ
    -0.07
    ird
    -0.07
    isel
    -0.07
    antly
    -0.07
    POSITIVE LOGITS
    çľĭä»ĸ
    0.13
    çľĭä½ł
    0.11
    æĹ¶ä»£ä¸ŃåĽ½
    0.11
    èĢĮè¨Ģ
    0.11
    å¦Ĥä½ķçľĭå¾ħ
    0.11
    è°ģèĥ½
    0.10
    ãĤĴè¦ĭãĤĭ
    0.10
    éħª
    0.10
    æĥħåĨµæĿ¥çľĭ
    0.10
    ä»Ģä¹ĪæŶåĢĻ
    0.10
    Activations Density 0.029%

    No Known Activations