© 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. 591
    Prev
    Next
    INDEX
    Explanations

    film ratings and classifications

    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
    çIJ®
    -0.09
    ucer
    -0.09
    客
    -0.09
    åĤij
    -0.08
    quist
    -0.08
    æ¼ı
    -0.08
    ungle
    -0.08
    Ñĩи
    -0.08
     Demp
    -0.08
    unts
    -0.08
    POSITIVE LOGITS
    尺度
    0.10
    ongan
    0.10
    éĤĪ
    0.09
     ÑĢазв
    0.09
    纯æ´ģ
    0.09
    Æ°a
    0.08
    对çħ§æ£ĢæŁ¥
    0.08
    å¤Ħå¤Ħ
    0.08
     /*!<
    0.08
    young
    0.08
    Activations Density 0.043%

    No Known Activations