© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115086
    Prev
    Next
    INDEX
    Explanations

    personal experiences and life events

    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
    osa
    -0.10
     nomin
    -0.10
    pend
    -0.09
     Ged
    -0.09
    icus
    -0.09
     Bryan
    -0.09
    prising
    -0.09
     persistent
    -0.09
    zu
    -0.09
    ju
    -0.09
    POSITIVE LOGITS
     personally
    0.12
    imat
    0.10
    agal
    0.10
     Finch
    0.09
    /us
    0.09
    eree
    0.09
    acho
    0.09
    antz
    0.09
     Mob
    0.09
     consc
    0.09
    Activations Density 0.158%

    No Known Activations