© 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. 10448
    Prev
    Next
    INDEX
    Explanations

    undermine or subvert

    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¸įçķĻ
    -0.11
    è¿Ļæł·æīįèĥ½
    -0.10
    æĮ¯ãĤĬ
    -0.09
    ayout
    -0.09
    isma
    -0.09
    orno
    -0.09
    line
    -0.09
    ä¸Ĭä¸ĭ
    -0.09
    çĸ®
    -0.09
    çķĮçļĦ
    -0.08
    POSITIVE LOGITS
    STER
    0.10
    秩
    0.09
    ä¸įäºĨ
    0.08
    ðŁı»
    0.08
    ëįĶ
    0.08
    ewood
    0.08
    çİ°è¡Į
    0.08
     conventional
    0.08
    heck
    0.08
    ochond
    0.08
    Activations Density 0.005%

    No Known Activations