© 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. 113387
    Prev
    Next
    INDEX
    Explanations

    identification details

    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
     reve
    -0.09
    UDA
    -0.09
     trav
    -0.08
     Recon
    -0.08
    aar
    -0.08
    addGroup
    -0.08
     porter
    -0.08
    ream
    -0.08
     heavily
    -0.08
    -ton
    -0.08
    POSITIVE LOGITS
     surname
    0.17
     alias
    0.17
     aliases
    0.15
     lastname
    0.13
     Alias
    0.13
     age
    0.12
    alias
    0.12
     Age
    0.12
     nickname
    0.12
    Alias
    0.12
    Activations Density 0.038%

    No Known Activations