© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 13909
    Prev
    Next
    INDEX
    Explanations

    positive sentiment and evaluation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
     Zur
    -0.10
    ê
    -0.10
     ceremon
    -0.10
     Kurd
    -0.10
     ));
    -0.10
     abbreviated
    -0.10
     );
    -0.10
    çŃ¾
    -0.09
     domina
    -0.09
     unfavorable
    -0.09
    POSITIVE LOGITS
     excellent
    0.30
     interesting
    0.29
     Interesting
    0.27
     Excellent
    0.26
    Excellent
    0.26
     fascinating
    0.24
    Interesting
    0.24
    interesting
    0.24
     thank
    0.23
     wonderful
    0.23
    Activations Density 0.317%

    No Known Activations