© 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. 60851
    Prev
    Next
    INDEX
    Explanations

    negative emotions and states

    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
    лÑİд
    -0.09
    ardi
    -0.09
    åŃIJå¼Ł
    -0.08
    严éĩįå½±åĵį
    -0.08
    ä¸ĢèĦ¸
    -0.08
    uard
    -0.08
    online
    -0.08
    èĦ¸èī²
    -0.08
    شر
    -0.08
    raham
    -0.07
    POSITIVE LOGITS
    è¹Ī
    0.09
    åIJİèĢħ
    0.09
    æī©
    0.09
    è¾ĺ
    0.09
    åĬ¨éĿĻ
    0.09
    çĦī
    0.09
    èĬĻèĵī
    0.08
    æij½
    0.08
     brief
    0.08
    æĪij对
    0.08
    Activations Density 0.183%

    No Known Activations