© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59354
    Prev
    Next
    INDEX
    Explanations

    climate change

    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
    Negative Logits
    ness
    -0.13
    åħħ足çļĦ
    -0.13
    CISION
    -0.12
    çĨ
    -0.10
    æĻĭåįĩ
    -0.10
    lic
    -0.10
    éķ¿éķ¿
    -0.09
    зов
    -0.09
    é¹Ħ
    -0.09
    æĮ¯åħ´
    -0.09
    POSITIVE LOGITS
    ÙĬÙĪÙĨ
    0.10
    使èĢħ
    0.10
    éĿ¢åīį
    0.09
    .gov
    0.08
    -era
    0.08
    èĥĮæĻ¯
    0.08
    isz
    0.08
    -themed
    0.08
    ãĥIJãĥ©
    0.08
    ildo
    0.08
    Activations Density 0.009%

    No Known Activations