© 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. 15132
    Prev
    Next
    INDEX
    Explanations

    Category:

    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
    ↵↵
    -0.09
    ↵
    -0.09
     molec
    -0.08
     mo
    -0.07
     Âł
    -0.07
     hans
    -0.07
     Sud
    -0.07
     Holly
    -0.07
    Âł
    -0.07
     Babylon
    -0.07
    POSITIVE LOGITS
     liners
    0.12
    cxx
    0.11
     YY
    0.10
    enna
    0.10
    apon
    0.10
    imore
    0.09
    LOSS
    0.09
     unconscious
    0.09
    itore
    0.09
    eren
    0.09
    Activations Density 0.003%

    No Known Activations