© 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. 34968
    Prev
    Next
    INDEX
    Explanations

    climate and weather events

    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
     pill
    -0.10
    çĶŁæ¶¯
    -0.09
     peg
    -0.09
    enko
    -0.08
     pret
    -0.08
    .removeEventListener
    -0.08
    çŤ
    -0.08
    ÃľN
    -0.08
    污æŁĵ
    -0.08
     paved
    -0.08
    POSITIVE LOGITS
    ç¥ŀ
    0.10
    è´Łè´£ä»»
    0.09
    byter
    0.09
    èµĬ
    0.09
    ç¦Ħ
    0.09
    ç¥Ī祷
    0.08
    åĸľ
    0.08
    tmpl
    0.08
    æ¶Īæŀģ
    0.08
    èIJİ缩
    0.08
    Activations Density 0.049%

    No Known Activations