© 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. 60792
    Prev
    Next
    INDEX
    Explanations

    memory and encoding

    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
    åıijåĩº
    -0.10
    å¾ģæ±Ĥ
    -0.09
    ç§ī
    -0.09
    èŃ°
    -0.09
    涵
    -0.09
     Dipl
    -0.09
     зай
    -0.09
    ç¥ī
    -0.09
    ammed
    -0.09
    è®®
    -0.08
    POSITIVE LOGITS
    è®°å¿Ĩ
    0.12
    åĽŀå¿Ĩ
    0.10
    æĽ´å¤ļä¿¡æģ¯
    0.10
    è®°å¿ĨåĬĽ
    0.10
    rote
    0.09
     eyewitness
    0.09
     Memory
    0.09
     slot
    0.09
    çķĻ
    0.09
    -Encoding
    0.09
    Activations Density 0.203%

    No Known Activations