© 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. 40283
    Prev
    Next
    INDEX
    Explanations

    influence

    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
    çªĿ
    -0.09
     ASE
    -0.09
    rier
    -0.09
    èĢĹ
    -0.09
    çŃij
    -0.09
    RACT
    -0.09
    ASI
    -0.08
    advertisement
    -0.08
    _means
    -0.08
    emean
    -0.08
    POSITIVE LOGITS
     influence
    0.22
     influences
    0.22
    çļĦå½±åĵį
    0.21
     Influence
    0.21
     влиÑı
    0.20
    å½±åĵį
    0.18
     Influ
    0.18
     influenced
    0.16
    å½±éŁ¿
    0.16
     influencing
    0.14
    Activations Density 0.237%

    No Known Activations