© 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. 91247
    Prev
    Next
    INDEX
    Explanations

    do justice

    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
     when
    -0.11
     When
    -0.09
     WHEN
    -0.09
     Jug
    -0.09
     novelty
    -0.09
    When
    -0.09
     insiders
    -0.09
    uba
    -0.09
    when
    -0.08
     Doll
    -0.08
    POSITIVE LOGITS
     justice
    0.14
     underst
    0.11
     Justice
    0.10
     filmer
    0.10
    icious
    0.10
    nop
    0.10
    ocre
    0.10
     underestimated
    0.10
    elligence
    0.10
    Justice
    0.10
    Activations Density 0.007%

    No Known Activations