© 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. 40157
    Prev
    Next
    INDEX
    Explanations

    news followed by a colon or conjunction

    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
    æĩ
    -0.10
    çĭĻ
    -0.09
    çĭ¬
    -0.09
    หว
    -0.09
    пÑĢод
    -0.09
    åį±éĻ©
    -0.08
    cctor
    -0.08
    ç»°
    -0.08
    zej
    -0.08
    æ¶ī
    -0.08
    POSITIVE LOGITS
    éĢļçŁ¥
    0.13
    宣å¸ĥ
    0.13
    åijĬè¯ī大家
    0.13
    å®ĺ宣
    0.12
     inform
    0.11
    å¾ĹçŁ¥
    0.11
     announce
    0.11
     announcement
    0.11
     announces
    0.10
    èİ·æĤī
    0.10
    Activations Density 0.091%

    No Known Activations