© 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. 33031
    Prev
    Next
    INDEX
    Explanations

    disgusted, disgust, repulsive

    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
    ç©¿æ¢Ń
    -0.09
     há»ı
    -0.09
    åĩºåİ»
    -0.08
     apprec
    -0.08
    æı©
    -0.08
    被害
    -0.08
     gá»įn
    -0.08
    éĵ¿
    -0.08
     intim
    -0.08
    çĨĦ
    -0.08
    POSITIVE LOGITS
    ingly
    0.12
    å·´æĭī
    0.10
    uous
    0.10
    ively
    0.10
    ening
    0.10
    staking
    0.09
    ãģĹãģ¾ãģĦ
    0.09
    貫
    0.09
    alah
    0.08
    ycz
    0.08
    Activations Density 0.006%

    No Known Activations