© 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. 14074
    Prev
    Next
    INDEX
    Explanations

    degree of success or achievements

    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
    iese
    -0.08
    anan
    -0.08
     relief
    -0.08
     Relief
    -0.08
     fares
    -0.08
     reint
    -0.08
     dreadful
    -0.08
    ker
    -0.08
     Guild
    -0.08
     Surv
    -0.07
    POSITIVE LOGITS
     fame
    0.17
     envy
    0.17
     bestowed
    0.15
     trajectory
    0.15
     env
    0.15
     success
    0.14
     intoxic
    0.14
     undes
    0.13
     recognition
    0.13
     catapult
    0.13
    Activations Density 0.183%

    No Known Activations