© 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. 50445
    Prev
    Next
    INDEX
    Explanations

    equality or rights

    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
     Hag
    -0.11
     "[
    -0.11
    arring
    -0.10
    TA
    -0.10
    erals
    -0.10
     Parish
    -0.10
     Potter
    -0.10
     Pere
    -0.10
    -js
    -0.10
    prene
    -0.10
    POSITIVE LOGITS
     oblig
    0.08
     cons
    0.08
     unb
    0.08
     Roth
    0.08
     obl
    0.08
     Tart
    0.08
     ing
    0.08
    azo
    0.08
    depend
    0.08
     den
    0.07
    Activations Density 0.007%

    No Known Activations