© 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. 5320
    Prev
    Next
    INDEX
    Explanations

    this followed by project, study, research

    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
    人家
    -0.09
    æĹ¢æľī
    -0.08
    trap
    -0.08
    éĥ¨ä¸»ä»»
    -0.08
    ç³Ĭ
    -0.08
    ï¼ł
    -0.08
    åĸĥ
    -0.08
    好åIJĹ
    -0.08
    åħ¸åŀĭ
    -0.08
    ANA
    -0.08
    POSITIVE LOGITS
    warts
    0.10
     article
    0.09
    è¿Ļç¯ĩæĸĩç«ł
    0.09
    ä»ĭç»į
    0.09
    ç¯ĩæĸĩç«ł
    0.09
    åĬłå¤§å¯¹
    0.09
     brief
    0.09
    çĹŀ
    0.09
    è¿ĻéĩĮ
    0.09
     ÑģÑĤаÑĤÑĮ
    0.09
    Activations Density 0.340%

    No Known Activations