© 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. 25651
    Prev
    Next
    INDEX
    Explanations

    organization, people, living

    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
    ivol
    -0.10
     Nem
    -0.09
    Plus
    -0.09
    ï¼ģ
    -0.09
    eses
    -0.09
    !]
    -0.09
     ultra
    -0.09
    !/
    -0.09
    sects
    -0.09
     lateral
    -0.09
    POSITIVE LOGITS
    haft
    0.09
     portion
    0.09
     homosex
    0.08
    reib
    0.08
    itle
    0.08
    bigint
    0.08
     plage
    0.08
     hitch
    0.07
     pregn
    0.07
     embar
    0.07
    Activations Density 0.016%

    No Known Activations