© 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. 63889
    Prev
    Next
    INDEX
    Explanations

    un- prefix followed by negative connotations

    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
    aceous
    -0.09
    ician
    -0.08
    纳æĸ¯
    -0.08
     ilk
    -0.08
    mers
    -0.08
    ssue
    -0.08
    eras
    -0.08
    ization
    -0.08
    ä¸įçķĻ
    -0.08
    atan
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.11
    بار
    0.10
    kie
    0.10
    èł¢
    0.09
    ears
    0.09
     à¹Ĩ
    0.09
    ly
    0.09
    iven
    0.09
    uent
    0.09
    çĥĬ
    0.08
    Activations Density 0.015%

    No Known Activations