© 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. 27145
    Prev
    Next
    INDEX
    Explanations

    chemical waste and environmental impact

    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
    çĮ·
    -0.08
    åĪĴå®ļ
    -0.08
    obia
    -0.07
    è¦Ĩ
    -0.07
    rias
    -0.07
    èĢĻ
    -0.07
    affles
    -0.07
    绣ä¸Ģ
    -0.07
    baugh
    -0.07
    Stat
    -0.07
    POSITIVE LOGITS
    еÑĢи
    0.11
    è¶Ĭ好
    0.10
    åºŁçī©
    0.09
     ÑģпиÑģ
    0.09
    å®ŀçī©
    0.09
    éĺµéĺµ
    0.09
    erah
    0.09
    忽
    0.09
    åħįè´£
    0.09
    ноп
    0.09
    Activations Density 0.058%

    No Known Activations