© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 116137
    Prev
    Next
    INDEX
    Explanations

    variables, measures, scores

    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
    Not in Any Lists

    No Comments

    Negative Logits
     debunk
    -0.14
     scientific
    -0.10
     incon
    -0.10
     sk
    -0.10
     paradox
    -0.10
     evolutionary
    -0.10
     dispro
    -0.09
     Leap
    -0.09
     coordinated
    -0.09
     Ferm
    -0.08
    POSITIVE LOGITS
     measures
    0.17
     cov
    0.17
     measure
    0.17
     variables
    0.16
     proxies
    0.16
     proxy
    0.16
     measured
    0.15
     Measures
    0.15
     scores
    0.14
    measure
    0.14
    Activations Density 9.812%

    No Known Activations