© 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. 117514
    Prev
    Next
    INDEX
    Explanations

    delivery options

    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
     slap
    -0.12
    Forbidden
    -0.11
     Forbidden
    -0.11
    illac
    -0.10
    lags
    -0.10
     Nit
    -0.10
     covert
    -0.10
     irgend
    -0.10
     slapped
    -0.10
     exiting
    -0.10
    POSITIVE LOGITS
     sol
    0.10
    _plate
    0.08
    )throws
    0.08
     allergic
    0.08
     knit
    0.08
    orio
    0.08
     kn
    0.07
    åij
    0.07
     Experiment
    0.07
    -yellow
    0.07
    Activations Density 0.326%

    No Known Activations