© 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. 116107
    Prev
    Next
    INDEX
    Explanations

    sample demographic characteristics

    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
     MANY
    -0.11
    Sink
    -0.11
     billions
    -0.11
     dashed
    -0.10
    atk
    -0.10
     fool
    -0.10
    ITA
    -0.10
     dotted
    -0.10
     lips
    -0.10
     traged
    -0.10
    POSITIVE LOGITS
     randomly
    0.21
     representative
    0.17
     volunteers
    0.17
     undergraduate
    0.16
     sampled
    0.16
     recruited
    0.16
     samples
    0.16
     sample
    0.15
     random
    0.15
     selected
    0.15
    Activations Density 4.482%

    No Known Activations