© 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. 47944
    Prev
    Next
    INDEX
    Explanations

    thanks for comment

    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
     adm
    -0.11
     Stap
    -0.09
     ste
    -0.09
     Admir
    -0.09
     sorry
    -0.09
     ADM
    -0.08
    ADM
    -0.08
     quantity
    -0.08
     apolog
    -0.08
     admiration
    -0.08
    POSITIVE LOGITS
    pty
    0.11
     likewise
    0.11
     collapses
    0.10
     sentiment
    0.10
    (fl
    0.10
     overs
    0.10
    loquent
    0.10
    _mr
    0.10
    lac
    0.10
     acceptance
    0.10
    Activations Density 0.016%

    No Known Activations