© 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. 7745
    Prev
    Next
    INDEX
    Explanations

    judging or judging by

    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
     sund
    -0.11
     validations
    -0.11
    into
    -0.11
     Mish
    -0.10
     estimation
    -0.10
     checks
    -0.10
     praises
    -0.09
     Checks
    -0.09
     á
    -0.09
    tog
    -0.09
    POSITIVE LOGITS
     based
    0.16
     harsh
    0.15
     negatively
    0.15
     differently
    0.15
     Based
    0.12
     adversely
    0.12
     poorly
    0.11
     unfavor
    0.11
    based
    0.11
     positively
    0.11
    Activations Density 0.023%

    No Known Activations