© 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. 35391
    Prev
    Next
    INDEX
    Explanations

    interactions and interact

    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«Ļ
    -0.10
    ä¾ĿçĦ¶æĺ¯
    -0.10
    å½ĵä¹ĭ
    -0.10
    MENT
    -0.09
    ç«ĭåľº
    -0.09
    Ñĩем
    -0.09
    ç«ĭæ¡Ī
    -0.09
     Complaint
    -0.09
    CADE
    -0.08
    çĤİ
    -0.08
    POSITIVE LOGITS
    交äºĴ
    0.17
    Interaction
    0.17
    interaction
    0.16
     interaction
    0.16
     Interaction
    0.14
     interactions
    0.14
     interact
    0.13
    _interaction
    0.13
    äºĴåĬ¨
    0.13
    æķĪåºĶ
    0.13
    Activations Density 0.141%

    No Known Activations