© 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. 23952
    Prev
    Next
    INDEX
    Explanations

    confused or confusing

    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
    说æĪij
    -0.09
    owell
    -0.09
    åĵģä½į
    -0.09
    æ¶ij
    -0.08
    解æĶ¾
    -0.08
    æĸ°æµªå¾®åįļ
    -0.08
    åįłæľī
    -0.08
    åĽ½å®ī
    -0.08
    aney
    -0.08
    èĥ½åģļåĪ°
    -0.08
    POSITIVE LOGITS
     confusion
    0.24
    æ··æ·Ĩ
    0.22
    è¿·æĥij
    0.21
    误导
    0.20
    æĥij
    0.19
     confusing
    0.19
    åĽ°æĥij
    0.19
     confuse
    0.17
     confused
    0.15
    æ··ä¹±
    0.15
    Activations Density 0.152%

    No Known Activations