© 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. 19351
    Prev
    Next
    INDEX
    Explanations

    negative sentiment descriptors

    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
    ring
    -0.09
    èī¯
    -0.09
    ris
    -0.09
    unity
    -0.08
    omap
    -0.08
    uns
    -0.08
    zw
    -0.08
    ays
    -0.08
    dep
    -0.08
     sno
    -0.08
    POSITIVE LOGITS
    åѤç«ĭ
    0.11
    auce
    0.11
    -looking
    0.11
    ness
    0.10
    NESS
    0.10
    ä½ŀ
    0.10
    å·´å·´
    0.10
    èĽ°
    0.10
    CastException
    0.10
    èĩªç§ģ
    0.09
    Activations Density 0.007%

    No Known Activations