© 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. 737
    Prev
    Next
    INDEX
    Explanations

    belief or skepticism

    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
     Bund
    -0.10
    è§ĦåĪĴ
    -0.10
    è¦ıåĬĥ
    -0.09
    _FILL
    -0.09
    æĶ¹æŃ£
    -0.09
     ÑĢазв
    -0.09
    (Be
    -0.09
    âĺī
    -0.09
    ç³
    -0.09
    .priv
    -0.09
    POSITIVE LOGITS
    ä¸įçĽ¸ä¿¡
    0.28
    ä¸įä¿¡
    0.19
    æĢĢçĸij
    0.18
    ä¿¡ä»»
    0.16
     skeptical
    0.15
     disbelief
    0.15
    çĽ¸ä¿¡
    0.15
    åĿļä¿¡
    0.14
     skepticism
    0.14
    åı¯ä¿¡
    0.14
    Activations Density 0.083%

    No Known Activations