© 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. 4200
    Prev
    Next
    INDEX
    Explanations

    solve equations

    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
    Styled
    -0.10
    alta
    -0.09
    anka
    -0.09
    bia
    -0.09
     retries
    -0.09
     iv
    -0.08
    enko
    -0.08
    ayas
    -0.08
     Aub
    -0.08
    vert
    -0.08
    POSITIVE LOGITS
     Scha
    0.09
     slip
    0.09
     metaph
    0.09
    [âĢ¦]
    0.09
    backs
    0.09
     Hij
    0.09
     Slip
    0.09
     Cath
    0.08
    Ě
    0.08
    /index
    0.08
    Activations Density 0.005%

    No Known Activations