© 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. 49669
    Prev
    Next
    INDEX
    Explanations

    not caring or impartial

    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
    af
    -0.08
     covert
    -0.08
     Hope
    -0.08
     entrenched
    -0.07
    roy
    -0.07
     Py
    -0.07
     AN
    -0.07
     puzzle
    -0.07
    Py
    -0.07
    648
    -0.07
    POSITIVE LOGITS
     indiscrim
    0.29
     discriminate
    0.25
     cares
    0.23
     indifferent
    0.22
     doesn
    0.20
     disregard
    0.20
     oblivious
    0.20
     discrimin
    0.19
     indifference
    0.19
     impartial
    0.19
    Activations Density 0.197%

    No Known Activations