© 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. 64140
    Prev
    Next
    INDEX
    Explanations

    hot shot contest

    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
    æ²ī
    -0.10
    zl
    -0.10
    odel
    -0.09
    档次
    -0.09
    cient
    -0.08
    褰
    -0.08
    被æīĵ
    -0.08
    ÑĦоÑĢм
    -0.08
    ChangeEvent
    -0.08
     Proud
    -0.08
    POSITIVE LOGITS
    çĤ½
    0.15
    -hot
    0.14
     HOT
    0.12
    åĩºçĤī
    0.12
    Hot
    0.12
     hot
    0.11
     Hot
    0.11
     nóng
    0.11
    çĤĻ
    0.11
    hot
    0.11
    Activations Density 0.059%

    No Known Activations