© 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. 54890
    Prev
    Next
    INDEX
    Explanations

    sustainable and unsustainable outcomes

    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
    ets
    -0.09
    å¸Ń
    -0.09
    Draft
    -0.09
    draft
    -0.09
    .tele
    -0.08
    -lo
    -0.08
    åħ¥
    -0.08
    åŃ£
    -0.08
     tele
    -0.08
     Draft
    -0.08
    POSITIVE LOGITS
    åı¯æĮģç»Ń
    0.19
     sustainable
    0.16
    éķ¿ä¹ħ
    0.16
     sustain
    0.15
    ustainable
    0.14
     sustainability
    0.14
    ustainability
    0.13
    à¹Ħหว
    0.12
     Sustainability
    0.12
     Sustainable
    0.12
    Activations Density 0.063%

    No Known Activations