© 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. 47634
    Prev
    Next
    INDEX
    Explanations

    can be, however, not, but

    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
    çīĮ
    -0.09
    acin
    -0.09
    è¿ĺæľīä»Ģä¹Ī
    -0.09
    ä¸įæħİ
    -0.08
    åįij
    -0.08
    åı£å¾Ħ
    -0.08
    ä¸įä¸Ģæł·çļĦ
    -0.08
    çĵ·
    -0.08
    fal
    -0.08
    onna
    -0.08
    POSITIVE LOGITS
    çijķ
    0.14
    ä¸įå½±åĵį
    0.12
    è¿ĻäºĽéĹ®é¢ĺ
    0.12
    è¿ĻçĤ¹
    0.12
    è¿Ļ个éĹ®é¢ĺ
    0.12
    è¿Ļç§įæĥħåĨµ
    0.11
    åħĭæľį
    0.10
    没åħ³ç³»
    0.10
     remedy
    0.10
    èĩ´åij½
    0.10
    Activations Density 0.064%

    No Known Activations