© 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. 50147
    Prev
    Next
    INDEX
    Explanations

    as an example

    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
     Gus
    -0.11
    Lint
    -0.10
    olg
    -0.10
    itag
    -0.10
    708
    -0.10
    lush
    -0.10
     sooner
    -0.10
    ased
    -0.09
     volte
    -0.09
     nip
    -0.09
    POSITIVE LOGITS
     guide
    0.44
     guiding
    0.41
     guides
    0.37
     guidance
    0.34
    guide
    0.33
     Guide
    0.31
    guid
    0.29
    Guide
    0.28
     Guides
    0.28
    -guide
    0.27
    Activations Density 0.289%

    No Known Activations